sha
stringlengths 40
40
| text
stringlengths 1
13.4M
| id
stringlengths 2
117
| tags
listlengths 1
7.91k
| created_at
stringlengths 25
25
| metadata
stringlengths 2
875k
| last_modified
stringlengths 25
25
| arxiv
listlengths 0
25
| languages
listlengths 0
7.91k
| tags_str
stringlengths 17
159k
| text_str
stringlengths 1
447k
| text_lists
listlengths 0
352
| processed_texts
listlengths 1
353
| tokens_length
listlengths 1
353
| input_texts
listlengths 1
40
|
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
1e17dd1804320b343828bd5c92184fe83113d73c |
Test | TeamA/dataset | [
"region:us"
] | 2023-11-29T16:25:48+00:00 | {"configs": [{"config_name": "default", "data_files": [{"split": "Museums", "path": "Museums.csv"}, {"split": "Medieval", "path": "Medieval.csv"}, {"split": "Rivers", "path": "Rivers.csv"}, {"split": "Public", "path": "Public.csv"}, {"split": "Square", "path": "Square.csv"}, {"split": "Bridges", "path": "Bridges.csv"}, {"split": "Murials", "path": "Murials.csv"}, {"split": "Parks", "path": "Parks.csv"}, {"split": "Beaches", "path": "Beaches.csv"}]}]} | 2023-12-11T13:46:34+00:00 | [] | [] | TAGS
#region-us
|
Test | [] | [
"TAGS\n#region-us \n"
] | [
6
] | [
"passage: TAGS\n#region-us \n"
] |
b94c1a8f295eadbde299a1ab8476c8a08892ef78 | # Dataset Card for "hh-rlhf-h4"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | HuggingFaceH4/hh-rlhf-h4 | [
"region:us"
] | 2023-11-29T16:25:52+00:00 | {"dataset_info": {"features": [{"name": "chosen", "list": [{"name": "content", "dtype": "string"}, {"name": "role", "dtype": "string"}]}, {"name": "rejected", "list": [{"name": "content", "dtype": "string"}, {"name": "role", "dtype": "string"}]}, {"name": "messages", "list": [{"name": "content", "dtype": "string"}, {"name": "role", "dtype": "string"}]}], "splits": [{"name": "train", "num_bytes": 472329144, "num_examples": 160800}, {"name": "test", "num_bytes": 25348918, "num_examples": 8552}], "download_size": 0, "dataset_size": 497678062}} | 2023-11-29T16:33:41+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "hh-rlhf-h4"
More Information needed | [
"# Dataset Card for \"hh-rlhf-h4\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"hh-rlhf-h4\"\n\nMore Information needed"
] | [
6,
18
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"hh-rlhf-h4\"\n\nMore Information needed"
] |
75bfd62475c45a683d715a5d71567583139b5f11 | # Dataset Card for "vhac-v1.0"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | llm4fun/vhac-v1.0 | [
"region:us"
] | 2023-11-29T17:00:08+00:00 | {"configs": [{"config_name": "default", "data_files": [{"split": "train", "path": "data/train-*"}]}], "dataset_info": {"features": [{"name": "instruction", "dtype": "string"}, {"name": "output", "dtype": "string"}, {"name": "translated", "dtype": "bool"}, {"name": "output_len", "dtype": "int64"}, {"name": "source", "dtype": "string"}, {"name": "input", "dtype": "string"}], "splits": [{"name": "train", "num_bytes": 327564182, "num_examples": 100000}], "download_size": 157597355, "dataset_size": 327564182}} | 2023-11-29T17:00:22+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "vhac-v1.0"
More Information needed | [
"# Dataset Card for \"vhac-v1.0\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"vhac-v1.0\"\n\nMore Information needed"
] | [
6,
16
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"vhac-v1.0\"\n\nMore Information needed"
] |
b1ecd8793bfaf940d8a852a326285bbf27a900de | # Dataset Card for "learning_row_test"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | tr416/learning_row_test | [
"region:us"
] | 2023-11-29T17:06:38+00:00 | {"dataset_info": {"features": [{"name": "instruction", "dtype": "string"}, {"name": "output", "dtype": "string"}], "splits": [{"name": "train", "num_bytes": 99219.44180386058, "num_examples": 101}], "download_size": 59638, "dataset_size": 99219.44180386058}, "configs": [{"config_name": "default", "data_files": [{"split": "train", "path": "data/train-*"}]}]} | 2023-11-29T17:06:40+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "learning_row_test"
More Information needed | [
"# Dataset Card for \"learning_row_test\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"learning_row_test\"\n\nMore Information needed"
] | [
6,
15
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"learning_row_test\"\n\nMore Information needed"
] |
ce025f7623a7eb0ec24afd7cde72b4bafedccd6b | # Dataset Card for "test_learner"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | tr416/test_learner | [
"region:us"
] | 2023-11-29T17:12:53+00:00 | {"dataset_info": {"features": [{"name": "instruction", "dtype": "string"}, {"name": "output", "dtype": "string"}], "splits": [{"name": "train", "num_bytes": 100944, "num_examples": 102}], "download_size": 59945, "dataset_size": 100944}, "configs": [{"config_name": "default", "data_files": [{"split": "train", "path": "data/train-*"}]}]} | 2023-11-29T17:12:55+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "test_learner"
More Information needed | [
"# Dataset Card for \"test_learner\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"test_learner\"\n\nMore Information needed"
] | [
6,
15
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"test_learner\"\n\nMore Information needed"
] |
f304ce59671d155273c861746581faa354d8a9af | # Dataset Card for "ultrafeedback_binarized_cleaned"
**Update 1/12/2023**: I've removed examples identified as faulty by Argilla - see [their awesome work](https://huggingface.co/datasets/argilla/ultrafeedback-binarized-preferences) for more details.
This is a version of the [UltraFeedback binarized dataset](https://huggingface.co/datasets/HuggingFaceH4/ultrafeedback_binarized) but with TruthfulQA prompts removed and source annotations added (so you can filter out samples from different sources yourself if you want!).
Please see the [binarized dataset card for more information](https://huggingface.co/datasets/HuggingFaceH4/ultrafeedback_binarized), or the [original UltraFeedback dataset card](https://huggingface.co/datasets/openbmb/UltraFeedback). | allenai/ultrafeedback_binarized_cleaned | [
"license:mit",
"region:us"
] | 2023-11-29T18:03:33+00:00 | {"license": "mit", "configs": [{"config_name": "default", "data_files": [{"split": "train_sft", "path": "data/train_sft-*"}, {"split": "test_sft", "path": "data/test_sft-*"}, {"split": "train_gen", "path": "data/train_gen-*"}, {"split": "test_gen", "path": "data/test_gen-*"}, {"split": "train_prefs", "path": "data/train_prefs-*"}, {"split": "test_prefs", "path": "data/test_prefs-*"}]}], "dataset_info": {"features": [{"name": "prompt", "dtype": "string"}, {"name": "prompt_id", "dtype": "string"}, {"name": "chosen", "list": [{"name": "content", "dtype": "string"}, {"name": "role", "dtype": "string"}]}, {"name": "rejected", "list": [{"name": "content", "dtype": "string"}, {"name": "role", "dtype": "string"}]}, {"name": "messages", "list": [{"name": "content", "dtype": "string"}, {"name": "role", "dtype": "string"}]}, {"name": "score_chosen", "dtype": "float64"}, {"name": "score_rejected", "dtype": "float64"}, {"name": "source", "dtype": "string"}], "splits": [{"name": "train_sft", "num_bytes": 393926052.7984401, "num_examples": 60829}, {"name": "test_sft", "num_bytes": 6230841.363636363, "num_examples": 985}, {"name": "train_gen", "num_bytes": 314344767.49216783, "num_examples": 60829}, {"name": "test_gen", "num_bytes": 4982506.090909091, "num_examples": 985}, {"name": "train_prefs", "num_bytes": 393926052.7984401, "num_examples": 60829}, {"name": "test_prefs", "num_bytes": 12672623.615773508, "num_examples": 1964}], "download_size": 629736515, "dataset_size": 1126082844.1593668}} | 2023-12-01T18:42:09+00:00 | [] | [] | TAGS
#license-mit #region-us
| # Dataset Card for "ultrafeedback_binarized_cleaned"
Update 1/12/2023: I've removed examples identified as faulty by Argilla - see their awesome work for more details.
This is a version of the UltraFeedback binarized dataset but with TruthfulQA prompts removed and source annotations added (so you can filter out samples from different sources yourself if you want!).
Please see the binarized dataset card for more information, or the original UltraFeedback dataset card. | [
"# Dataset Card for \"ultrafeedback_binarized_cleaned\"\n\nUpdate 1/12/2023: I've removed examples identified as faulty by Argilla - see their awesome work for more details.\n\nThis is a version of the UltraFeedback binarized dataset but with TruthfulQA prompts removed and source annotations added (so you can filter out samples from different sources yourself if you want!).\n\nPlease see the binarized dataset card for more information, or the original UltraFeedback dataset card."
] | [
"TAGS\n#license-mit #region-us \n",
"# Dataset Card for \"ultrafeedback_binarized_cleaned\"\n\nUpdate 1/12/2023: I've removed examples identified as faulty by Argilla - see their awesome work for more details.\n\nThis is a version of the UltraFeedback binarized dataset but with TruthfulQA prompts removed and source annotations added (so you can filter out samples from different sources yourself if you want!).\n\nPlease see the binarized dataset card for more information, or the original UltraFeedback dataset card."
] | [
11,
116
] | [
"passage: TAGS\n#license-mit #region-us \n# Dataset Card for \"ultrafeedback_binarized_cleaned\"\n\nUpdate 1/12/2023: I've removed examples identified as faulty by Argilla - see their awesome work for more details.\n\nThis is a version of the UltraFeedback binarized dataset but with TruthfulQA prompts removed and source annotations added (so you can filter out samples from different sources yourself if you want!).\n\nPlease see the binarized dataset card for more information, or the original UltraFeedback dataset card."
] |
4f43c63dae831a4d16ea640759a979bfd5469c48 |
# Dataset with 256x256 metal album covers.
I took the data from: https://www.kaggle.com/datasets/benjamnmachn/metal-albums-artwork
Dataset has 12813 images of 256x256 resolution.
Text description of image is: "\<Band\> - \<Album Name\>" | Alphonsce/metal_album_covers | [
"language:en",
"language:fi",
"language:no",
"license:apache-2.0",
"region:us"
] | 2023-11-29T18:06:07+00:00 | {"language": ["en", "fi", "no"], "license": "apache-2.0", "pretty_name": "MetAlbums", "dataset_info": {"features": [{"name": "image", "dtype": "image"}, {"name": "text", "dtype": "string"}], "splits": [{"name": "train", "num_bytes": 1457790757.579, "num_examples": 12813}], "download_size": 1442158271, "dataset_size": 1457790757.579}, "configs": [{"config_name": "default", "data_files": [{"split": "train", "path": "data/train-*"}]}]} | 2023-11-29T18:29:38+00:00 | [] | [
"en",
"fi",
"no"
] | TAGS
#language-English #language-Finnish #language-Norwegian #license-apache-2.0 #region-us
|
# Dataset with 256x256 metal album covers.
I took the data from: URL
Dataset has 12813 images of 256x256 resolution.
Text description of image is: "\<Band\> - \<Album Name\>" | [
"# Dataset with 256x256 metal album covers.\n\nI took the data from: URL\n\nDataset has 12813 images of 256x256 resolution.\n\nText description of image is: \"\\<Band\\> - \\<Album Name\\>\""
] | [
"TAGS\n#language-English #language-Finnish #language-Norwegian #license-apache-2.0 #region-us \n",
"# Dataset with 256x256 metal album covers.\n\nI took the data from: URL\n\nDataset has 12813 images of 256x256 resolution.\n\nText description of image is: \"\\<Band\\> - \\<Album Name\\>\""
] | [
30,
53
] | [
"passage: TAGS\n#language-English #language-Finnish #language-Norwegian #license-apache-2.0 #region-us \n# Dataset with 256x256 metal album covers.\n\nI took the data from: URL\n\nDataset has 12813 images of 256x256 resolution.\n\nText description of image is: \"\\<Band\\> - \\<Album Name\\>\""
] |
6bc3d031f1ff54ae3476d26fa58f5d2a08716282 | # LCA (Bug Localization)
This is the data for **Bug Localization** benchmark as part of LCA.
## How-to
1. Since the dataset is private, if you haven't used HF Hub before, add your token via `huggingface-cli` first:
```
huggingface-cli login
```
2. List all the available configs via [`datasets.get_dataset_config_names`](https://huggingface.co/docs/datasets/v2.14.3/en/package_reference/loading_methods#datasets.get_dataset_config_names) and choose an appropriate one
3. Load the data via [`load_dataset`](https://huggingface.co/docs/datasets/v2.14.3/en/package_reference/loading_methods#datasets.load_dataset):
```py
from datasets import load_dataset
# Select a configuration from ["py", "java", "kt", "mixed"]
configuration = "py"
# Select a split from ["dev", "train", "test"]
split = "dev"
# Load data
dataset = load_dataset("JetBrains-Research/lca-bug-localization", configuration, split=split)
```
4. Load repos via [`hf_hub_download`](https://huggingface.co/docs/huggingface_hub/v0.20.3/en/package_reference/file_download#huggingface_hub.hf_hub_download)
```py
from huggingface_hub import hf_hub_download
from datasets import load_dataset
# Load json with list of repos' .tar.gz file paths
paths_json = load_dataset("JetBrains-Research/lca-bug-localization", data_files="paths.json")
# Load each repo in .tar.gz format, unzip, delete archive
repos = paths_json["repos"][0]
for i, repo_tar_path in enumerate(repos):
local_repo_tars = hf_hub_download(
"JetBrains-Research/lca-bug-localization",
filename=repo_tar_path,
repo_type="dataset",
local_dir="local/dir"
)
result = subprocess.run(["tar", "-xzf", local_repo_tars, "-C", os.path.join("local/dir", "repos")])
os.remove(local_repo_tars)
```
## Dataset Structure
TODO: some overall structure or repo
### Bug localization data
This section concerns configuration with *full data* about each commit (no `-labels` suffix).
Each example has the following fields:
| **Field** | **Description** |
|:------------------:|:----------------------------------------:|
| `repo_owner` | Bug issue repository owner. |
| `repo_name` | Bug issue repository name. |
| `issue_url` | GitHub link to issue <br> `https://github.com/{repo_owner}/{repo_name}/issues/{issue_id}`. |
| `pull_url` | GitHub link to pull request <br> `https://github.com/{repo_owner}/{repo_name}/pull/{pull_id}`. |
| `comment_url` | GitHub link to comment with pull request to issue reference <br> `https://github.com/{repo_owner}/{repo_name}/pull/{pull_id}#issuecomment-{comment_id}`. |
| `issue_title` | Issue title. |
| `issue_body` | Issue body. |
| `base_sha` | Pull request base sha. |
| `head_sha` | Pull request head sha. |
| `diff_url` | Pull request diff url between base and head sha <br> `https://github.com/{repo_owner}/{repo_name}/compare/{base_sha}...{head_sha}`. |
| `diff` | Pull request diff content. |
| `changed_files` | List of changed files parsed from diff. |
| `changed_files_exts` | Dict from changed files extension to count. |
| `changed_files_count` | Number of changed files. |
| `java_changed_files_count` | Number of changed `.java` files. |
| `kt_changed_files_count` | Number of changed `.kt` files. |
| `py_changed_files_count` | Number of changed `.py` files. |
| `code_changed_files_count` | Number of changed `.java`, `.kt` or `.py` files. |
| `pull_create_at` | Data of pull request creation in format yyyy-mm-ddThh:mm:ssZ. |
| `stars` | Number of repo stars. |
### Repos data
TODO: describe repos data as `.tar.gz` archives with list of repos metadata | JetBrains-Research/lca-bug-localization | [
"task_categories:text-generation",
"language:en",
"license:other",
"code",
"region:us"
] | 2023-11-29T18:32:22+00:00 | {"language": ["en"], "license": "other", "task_categories": ["text-generation"], "pretty_name": "LCA (Bug Localization)", "tags": ["code"], "dataset_info": [{"config_name": "java", "features": [{"name": "id", "dtype": "int64"}, {"name": "repo_owner", "dtype": "string"}, {"name": "repo_name", "dtype": "string"}, {"name": "issue_url", "dtype": "string"}, {"name": "pull_url", "dtype": "string"}, {"name": "comment_url", "dtype": "string"}, {"name": "issue_title", "dtype": "string"}, {"name": "issue_body", "dtype": "string"}, {"name": "base_sha", "dtype": "string"}, {"name": "head_sha", "dtype": "string"}, {"name": "diff_url", "dtype": "string"}, {"name": "diff", "dtype": "string"}, {"name": "changed_files", "dtype": "string"}, {"name": "changed_files_exts", "dtype": "string"}, {"name": "changed_files_count", "dtype": "int64"}, {"name": "java_changed_files_count", "dtype": "int64"}, {"name": "kt_changed_files_count", "dtype": "int64"}, {"name": "py_changed_files_count", "dtype": "int64"}, {"name": "code_changed_files_count", "dtype": "int64"}, {"name": "pull_create_at", "dtype": "int64"}, {"name": "stars", "dtype": "int64"}], "splits": [{"name": "dev", "num_bytes": 4310928, "num_examples": 335}, {"name": "test", "num_bytes": 12868.441791044776, "num_examples": 1}, {"name": "train", "num_bytes": 4298059.558208955, "num_examples": 334}], "download_size": 7981103, "dataset_size": 8621856.0}, {"config_name": "kt", "features": [{"name": "id", "dtype": "int64"}, {"name": "repo_owner", "dtype": "string"}, {"name": "repo_name", "dtype": "string"}, {"name": "issue_url", "dtype": "string"}, {"name": "pull_url", "dtype": "string"}, {"name": "comment_url", "dtype": "string"}, {"name": "issue_title", "dtype": "string"}, {"name": "issue_body", "dtype": "string"}, {"name": "base_sha", "dtype": "string"}, {"name": "head_sha", "dtype": "string"}, {"name": "diff_url", "dtype": "string"}, {"name": "diff", "dtype": "string"}, {"name": "changed_files", "dtype": "string"}, {"name": "changed_files_exts", "dtype": "string"}, {"name": "changed_files_count", "dtype": "int64"}, {"name": "java_changed_files_count", "dtype": "int64"}, {"name": "kt_changed_files_count", "dtype": "int64"}, {"name": "py_changed_files_count", "dtype": "int64"}, {"name": "code_changed_files_count", "dtype": "int64"}, {"name": "pull_create_at", "dtype": "int64"}, {"name": "stars", "dtype": "int64"}], "splits": [{"name": "dev", "num_bytes": 270236, "num_examples": 35}, {"name": "test", "num_bytes": 7721.028571428571, "num_examples": 1}, {"name": "train", "num_bytes": 262514.97142857144, "num_examples": 34}], "download_size": 819327, "dataset_size": 540472.0000000001}, {"config_name": "mixed", "features": [{"name": "id", "dtype": "int64"}, {"name": "repo_owner", "dtype": "string"}, {"name": "repo_name", "dtype": "string"}, {"name": "issue_url", "dtype": "string"}, {"name": "pull_url", "dtype": "string"}, {"name": "comment_url", "dtype": "string"}, {"name": "issue_title", "dtype": "string"}, {"name": "issue_body", "dtype": "string"}, {"name": "base_sha", "dtype": "string"}, {"name": "head_sha", "dtype": "string"}, {"name": "diff_url", "dtype": "string"}, {"name": "diff", "dtype": "string"}, {"name": "changed_files", "dtype": "string"}, {"name": "changed_files_exts", "dtype": "string"}, {"name": "changed_files_count", "dtype": "int64"}, {"name": "java_changed_files_count", "dtype": "int64"}, {"name": "kt_changed_files_count", "dtype": "int64"}, {"name": "py_changed_files_count", "dtype": "int64"}, {"name": "code_changed_files_count", "dtype": "int64"}, {"name": "pull_create_at", "dtype": "int64"}, {"name": "stars", "dtype": "int64"}], "splits": [{"name": "dev", "num_bytes": 93329021, "num_examples": 641}, {"name": "test", "num_bytes": 145599.09672386895, "num_examples": 1}, {"name": "train", "num_bytes": 93183421.90327613, "num_examples": 640}], "download_size": 250571391, "dataset_size": 186658042.0}, {"config_name": "py", "features": [{"name": "id", "dtype": "int64"}, {"name": "repo_owner", "dtype": "string"}, {"name": "repo_name", "dtype": "string"}, {"name": "issue_url", "dtype": "string"}, {"name": "pull_url", "dtype": "string"}, {"name": "comment_url", "dtype": "string"}, {"name": "issue_title", "dtype": "string"}, {"name": "issue_body", "dtype": "string"}, {"name": "base_sha", "dtype": "string"}, {"name": "head_sha", "dtype": "string"}, {"name": "diff_url", "dtype": "string"}, {"name": "diff", "dtype": "string"}, {"name": "changed_files", "dtype": "string"}, {"name": "changed_files_exts", "dtype": "string"}, {"name": "changed_files_count", "dtype": "int64"}, {"name": "java_changed_files_count", "dtype": "int64"}, {"name": "kt_changed_files_count", "dtype": "int64"}, {"name": "py_changed_files_count", "dtype": "int64"}, {"name": "code_changed_files_count", "dtype": "int64"}, {"name": "pull_create_at", "dtype": "int64"}, {"name": "stars", "dtype": "int64"}], "splits": [{"name": "dev", "num_bytes": 7561415, "num_examples": 917}, {"name": "test", "num_bytes": 247374.5365321701, "num_examples": 30}, {"name": "train", "num_bytes": 7314040.46346783, "num_examples": 887}], "download_size": 17989650, "dataset_size": 15122830.0}], "configs": [{"config_name": "java", "data_files": [{"split": "dev", "path": "java/dev-*"}, {"split": "test", "path": "java/test-*"}, {"split": "train", "path": "java/train-*"}]}, {"config_name": "kt", "data_files": [{"split": "dev", "path": "kt/dev-*"}, {"split": "test", "path": "kt/test-*"}, {"split": "train", "path": "kt/train-*"}]}, {"config_name": "mixed", "data_files": [{"split": "dev", "path": "mixed/dev-*"}, {"split": "test", "path": "mixed/test-*"}, {"split": "train", "path": "mixed/train-*"}]}, {"config_name": "py", "data_files": [{"split": "dev", "path": "py/dev-*"}, {"split": "test", "path": "py/test-*"}, {"split": "train", "path": "py/train-*"}]}]} | 2024-01-31T17:42:15+00:00 | [] | [
"en"
] | TAGS
#task_categories-text-generation #language-English #license-other #code #region-us
| LCA (Bug Localization)
======================
This is the data for Bug Localization benchmark as part of LCA.
How-to
------
1. Since the dataset is private, if you haven't used HF Hub before, add your token via 'huggingface-cli' first:
2. List all the available configs via 'datasets.get\_dataset\_config\_names' and choose an appropriate one
3. Load the data via 'load\_dataset':
4. Load repos via 'hf\_hub\_download'
Dataset Structure
-----------------
TODO: some overall structure or repo
### Bug localization data
This section concerns configuration with *full data* about each commit (no '-labels' suffix).
Each example has the following fields:
### Repos data
TODO: describe repos data as '.URL' archives with list of repos metadata
| [
"### Bug localization data\n\n\nThis section concerns configuration with *full data* about each commit (no '-labels' suffix).\n\n\nEach example has the following fields:",
"### Repos data\n\n\nTODO: describe repos data as '.URL' archives with list of repos metadata"
] | [
"TAGS\n#task_categories-text-generation #language-English #license-other #code #region-us \n",
"### Bug localization data\n\n\nThis section concerns configuration with *full data* about each commit (no '-labels' suffix).\n\n\nEach example has the following fields:",
"### Repos data\n\n\nTODO: describe repos data as '.URL' archives with list of repos metadata"
] | [
28,
38,
24
] | [
"passage: TAGS\n#task_categories-text-generation #language-English #license-other #code #region-us \n### Bug localization data\n\n\nThis section concerns configuration with *full data* about each commit (no '-labels' suffix).\n\n\nEach example has the following fields:### Repos data\n\n\nTODO: describe repos data as '.URL' archives with list of repos metadata"
] |
ff08f6703988b5691bd6b56c6febe1e4397982a0 |
# Bangumi Image Base of Skip Beat!
This is the image base of bangumi Skip Beat!, we detected 35 characters, 2822 images in total. The full dataset is [here](all.zip).
**Please note that these image bases are not guaranteed to be 100% cleaned, they may be noisy actual.** If you intend to manually train models using this dataset, we recommend performing necessary preprocessing on the downloaded dataset to eliminate potential noisy samples (approximately 1% probability).
Here is the characters' preview:
| # | Images | Download | Preview 1 | Preview 2 | Preview 3 | Preview 4 | Preview 5 | Preview 6 | Preview 7 | Preview 8 |
|:------|---------:|:---------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|
| 0 | 37 | [Download](0/dataset.zip) |  |  |  |  |  |  |  |  |
| 1 | 23 | [Download](1/dataset.zip) |  |  |  |  |  |  |  |  |
| 2 | 24 | [Download](2/dataset.zip) |  |  |  |  |  |  |  |  |
| 3 | 134 | [Download](3/dataset.zip) |  |  |  |  |  |  |  |  |
| 4 | 35 | [Download](4/dataset.zip) |  |  |  |  |  |  |  |  |
| 5 | 148 | [Download](5/dataset.zip) |  |  |  |  |  |  |  |  |
| 6 | 437 | [Download](6/dataset.zip) |  |  |  |  |  |  |  |  |
| 7 | 95 | [Download](7/dataset.zip) |  |  |  |  |  |  |  |  |
| 8 | 84 | [Download](8/dataset.zip) |  |  |  |  |  |  |  |  |
| 9 | 25 | [Download](9/dataset.zip) |  |  |  |  |  |  |  |  |
| 10 | 534 | [Download](10/dataset.zip) |  |  |  |  |  |  |  |  |
| 11 | 43 | [Download](11/dataset.zip) |  |  |  |  |  |  |  |  |
| 12 | 127 | [Download](12/dataset.zip) |  |  |  |  |  |  |  |  |
| 13 | 185 | [Download](13/dataset.zip) |  |  |  |  |  |  |  |  |
| 14 | 107 | [Download](14/dataset.zip) |  |  |  |  |  |  |  |  |
| 15 | 76 | [Download](15/dataset.zip) |  |  |  |  |  |  |  |  |
| 16 | 62 | [Download](16/dataset.zip) |  |  |  |  |  |  |  |  |
| 17 | 30 | [Download](17/dataset.zip) |  |  |  |  |  |  |  |  |
| 18 | 26 | [Download](18/dataset.zip) |  |  |  |  |  |  |  |  |
| 19 | 46 | [Download](19/dataset.zip) |  |  |  |  |  |  |  |  |
| 20 | 25 | [Download](20/dataset.zip) |  |  |  |  |  |  |  |  |
| 21 | 20 | [Download](21/dataset.zip) |  |  |  |  |  |  |  |  |
| 22 | 45 | [Download](22/dataset.zip) |  |  |  |  |  |  |  |  |
| 23 | 41 | [Download](23/dataset.zip) |  |  |  |  |  |  |  |  |
| 24 | 28 | [Download](24/dataset.zip) |  |  |  |  |  |  |  |  |
| 25 | 13 | [Download](25/dataset.zip) |  |  |  |  |  |  |  |  |
| 26 | 85 | [Download](26/dataset.zip) |  |  |  |  |  |  |  |  |
| 27 | 19 | [Download](27/dataset.zip) |  |  |  |  |  |  |  |  |
| 28 | 45 | [Download](28/dataset.zip) |  |  |  |  |  |  |  |  |
| 29 | 52 | [Download](29/dataset.zip) |  |  |  |  |  |  |  |  |
| 30 | 18 | [Download](30/dataset.zip) |  |  |  |  |  |  |  |  |
| 31 | 12 | [Download](31/dataset.zip) |  |  |  |  |  |  |  |  |
| 32 | 13 | [Download](32/dataset.zip) |  |  |  |  |  |  |  |  |
| 33 | 9 | [Download](33/dataset.zip) |  |  |  |  |  |  |  |  |
| noise | 119 | [Download](-1/dataset.zip) |  |  |  |  |  |  |  |  |
| BangumiBase/skipbeat | [
"size_categories:1K<n<10K",
"license:mit",
"art",
"region:us"
] | 2023-11-29T19:22:31+00:00 | {"license": "mit", "size_categories": ["1K<n<10K"], "tags": ["art"]} | 2023-11-29T20:51:54+00:00 | [] | [] | TAGS
#size_categories-1K<n<10K #license-mit #art #region-us
| Bangumi Image Base of Skip Beat!
================================
This is the image base of bangumi Skip Beat!, we detected 35 characters, 2822 images in total. The full dataset is here.
Please note that these image bases are not guaranteed to be 100% cleaned, they may be noisy actual. If you intend to manually train models using this dataset, we recommend performing necessary preprocessing on the downloaded dataset to eliminate potential noisy samples (approximately 1% probability).
Here is the characters' preview:
| [] | [
"TAGS\n#size_categories-1K<n<10K #license-mit #art #region-us \n"
] | [
25
] | [
"passage: TAGS\n#size_categories-1K<n<10K #license-mit #art #region-us \n"
] |
638fa12189fa83c3bab75e27aa069aa5acc2516d |
# Bangumi Image Base of Uchouten Kazoku
This is the image base of bangumi Uchouten Kazoku, we detected 51 characters, 4934 images in total. The full dataset is [here](all.zip).
**Please note that these image bases are not guaranteed to be 100% cleaned, they may be noisy actual.** If you intend to manually train models using this dataset, we recommend performing necessary preprocessing on the downloaded dataset to eliminate potential noisy samples (approximately 1% probability).
Here is the characters' preview:
| # | Images | Download | Preview 1 | Preview 2 | Preview 3 | Preview 4 | Preview 5 | Preview 6 | Preview 7 | Preview 8 |
|:------|---------:|:---------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|
| 0 | 336 | [Download](0/dataset.zip) |  |  |  |  |  |  |  |  |
| 1 | 35 | [Download](1/dataset.zip) |  |  |  |  |  |  |  |  |
| 2 | 105 | [Download](2/dataset.zip) |  |  |  |  |  |  |  |  |
| 3 | 32 | [Download](3/dataset.zip) |  |  |  |  |  |  |  |  |
| 4 | 1287 | [Download](4/dataset.zip) |  |  |  |  |  |  |  |  |
| 5 | 13 | [Download](5/dataset.zip) |  |  |  |  |  |  |  |  |
| 6 | 96 | [Download](6/dataset.zip) |  |  |  |  |  |  |  |  |
| 7 | 50 | [Download](7/dataset.zip) |  |  |  |  |  |  |  |  |
| 8 | 354 | [Download](8/dataset.zip) |  |  |  |  |  |  |  |  |
| 9 | 27 | [Download](9/dataset.zip) |  |  |  |  |  |  |  |  |
| 10 | 80 | [Download](10/dataset.zip) |  |  |  |  |  |  |  |  |
| 11 | 13 | [Download](11/dataset.zip) |  |  |  |  |  |  |  |  |
| 12 | 32 | [Download](12/dataset.zip) |  |  |  |  |  |  |  |  |
| 13 | 22 | [Download](13/dataset.zip) |  |  |  |  |  |  |  |  |
| 14 | 25 | [Download](14/dataset.zip) |  |  |  |  |  |  |  |  |
| 15 | 355 | [Download](15/dataset.zip) |  |  |  |  |  |  |  |  |
| 16 | 206 | [Download](16/dataset.zip) |  |  |  |  |  |  |  |  |
| 17 | 250 | [Download](17/dataset.zip) |  |  |  |  |  |  |  |  |
| 18 | 43 | [Download](18/dataset.zip) |  |  |  |  |  |  |  |  |
| 19 | 33 | [Download](19/dataset.zip) |  |  |  |  |  |  |  |  |
| 20 | 30 | [Download](20/dataset.zip) |  |  |  |  |  |  |  |  |
| 21 | 56 | [Download](21/dataset.zip) |  |  |  |  |  |  |  |  |
| 22 | 84 | [Download](22/dataset.zip) |  |  |  |  |  |  |  |  |
| 23 | 21 | [Download](23/dataset.zip) |  |  |  |  |  |  |  |  |
| 24 | 129 | [Download](24/dataset.zip) |  |  |  |  |  |  |  |  |
| 25 | 43 | [Download](25/dataset.zip) |  |  |  |  |  |  |  |  |
| 26 | 97 | [Download](26/dataset.zip) |  |  |  |  |  |  |  |  |
| 27 | 14 | [Download](27/dataset.zip) |  |  |  |  |  |  |  |  |
| 28 | 48 | [Download](28/dataset.zip) |  |  |  |  |  |  |  |  |
| 29 | 18 | [Download](29/dataset.zip) |  |  |  |  |  |  |  |  |
| 30 | 130 | [Download](30/dataset.zip) |  |  |  |  |  |  |  |  |
| 31 | 19 | [Download](31/dataset.zip) |  |  |  |  |  |  |  |  |
| 32 | 84 | [Download](32/dataset.zip) |  |  |  |  |  |  |  |  |
| 33 | 8 | [Download](33/dataset.zip) |  |  |  |  |  |  |  |  |
| 34 | 20 | [Download](34/dataset.zip) |  |  |  |  |  |  |  |  |
| 35 | 37 | [Download](35/dataset.zip) |  |  |  |  |  |  |  |  |
| 36 | 31 | [Download](36/dataset.zip) |  |  |  |  |  |  |  |  |
| 37 | 23 | [Download](37/dataset.zip) |  |  |  |  |  |  |  |  |
| 38 | 9 | [Download](38/dataset.zip) |  |  |  |  |  |  |  |  |
| 39 | 13 | [Download](39/dataset.zip) |  |  |  |  |  |  |  |  |
| 40 | 17 | [Download](40/dataset.zip) |  |  |  |  |  |  |  |  |
| 41 | 314 | [Download](41/dataset.zip) |  |  |  |  |  |  |  |  |
| 42 | 9 | [Download](42/dataset.zip) |  |  |  |  |  |  |  |  |
| 43 | 14 | [Download](43/dataset.zip) |  |  |  |  |  |  |  |  |
| 44 | 7 | [Download](44/dataset.zip) |  |  |  |  |  |  |  | N/A |
| 45 | 8 | [Download](45/dataset.zip) |  |  |  |  |  |  |  |  |
| 46 | 13 | [Download](46/dataset.zip) |  |  |  |  |  |  |  |  |
| 47 | 33 | [Download](47/dataset.zip) |  |  |  |  |  |  |  |  |
| 48 | 16 | [Download](48/dataset.zip) |  |  |  |  |  |  |  |  |
| 49 | 82 | [Download](49/dataset.zip) |  |  |  |  |  |  |  |  |
| noise | 113 | [Download](-1/dataset.zip) |  |  |  |  |  |  |  |  |
| BangumiBase/uchoutenkazoku | [
"size_categories:1K<n<10K",
"license:mit",
"art",
"region:us"
] | 2023-11-29T19:23:05+00:00 | {"license": "mit", "size_categories": ["1K<n<10K"], "tags": ["art"]} | 2023-11-29T23:21:43+00:00 | [] | [] | TAGS
#size_categories-1K<n<10K #license-mit #art #region-us
| Bangumi Image Base of Uchouten Kazoku
=====================================
This is the image base of bangumi Uchouten Kazoku, we detected 51 characters, 4934 images in total. The full dataset is here.
Please note that these image bases are not guaranteed to be 100% cleaned, they may be noisy actual. If you intend to manually train models using this dataset, we recommend performing necessary preprocessing on the downloaded dataset to eliminate potential noisy samples (approximately 1% probability).
Here is the characters' preview:
| [] | [
"TAGS\n#size_categories-1K<n<10K #license-mit #art #region-us \n"
] | [
25
] | [
"passage: TAGS\n#size_categories-1K<n<10K #license-mit #art #region-us \n"
] |
b8adc37c10e0e76958f78564cee1a46b222506a2 |
# Bangumi Image Base of Fumetsu No Anata E
This is the image base of bangumi Fumetsu no Anata e, we detected 70 characters, 7434 images in total. The full dataset is [here](all.zip).
**Please note that these image bases are not guaranteed to be 100% cleaned, they may be noisy actual.** If you intend to manually train models using this dataset, we recommend performing necessary preprocessing on the downloaded dataset to eliminate potential noisy samples (approximately 1% probability).
Here is the characters' preview:
| # | Images | Download | Preview 1 | Preview 2 | Preview 3 | Preview 4 | Preview 5 | Preview 6 | Preview 7 | Preview 8 |
|:------|---------:|:---------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|
| 0 | 165 | [Download](0/dataset.zip) |  |  |  |  |  |  |  |  |
| 1 | 511 | [Download](1/dataset.zip) |  |  |  |  |  |  |  |  |
| 2 | 36 | [Download](2/dataset.zip) |  |  |  |  |  |  |  |  |
| 3 | 135 | [Download](3/dataset.zip) |  |  |  |  |  |  |  |  |
| 4 | 45 | [Download](4/dataset.zip) |  |  |  |  |  |  |  |  |
| 5 | 106 | [Download](5/dataset.zip) |  |  |  |  |  |  |  |  |
| 6 | 118 | [Download](6/dataset.zip) |  |  |  |  |  |  |  |  |
| 7 | 93 | [Download](7/dataset.zip) |  |  |  |  |  |  |  |  |
| 8 | 43 | [Download](8/dataset.zip) |  |  |  |  |  |  |  |  |
| 9 | 183 | [Download](9/dataset.zip) |  |  |  |  |  |  |  |  |
| 10 | 67 | [Download](10/dataset.zip) |  |  |  |  |  |  |  |  |
| 11 | 36 | [Download](11/dataset.zip) |  |  |  |  |  |  |  |  |
| 12 | 23 | [Download](12/dataset.zip) |  |  |  |  |  |  |  |  |
| 13 | 92 | [Download](13/dataset.zip) |  |  |  |  |  |  |  |  |
| 14 | 34 | [Download](14/dataset.zip) |  |  |  |  |  |  |  |  |
| 15 | 33 | [Download](15/dataset.zip) |  |  |  |  |  |  |  |  |
| 16 | 384 | [Download](16/dataset.zip) |  |  |  |  |  |  |  |  |
| 17 | 62 | [Download](17/dataset.zip) |  |  |  |  |  |  |  |  |
| 18 | 344 | [Download](18/dataset.zip) |  |  |  |  |  |  |  |  |
| 19 | 125 | [Download](19/dataset.zip) |  |  |  |  |  |  |  |  |
| 20 | 111 | [Download](20/dataset.zip) |  |  |  |  |  |  |  |  |
| 21 | 31 | [Download](21/dataset.zip) |  |  |  |  |  |  |  |  |
| 22 | 28 | [Download](22/dataset.zip) |  |  |  |  |  |  |  |  |
| 23 | 31 | [Download](23/dataset.zip) |  |  |  |  |  |  |  |  |
| 24 | 38 | [Download](24/dataset.zip) |  |  |  |  |  |  |  |  |
| 25 | 80 | [Download](25/dataset.zip) |  |  |  |  |  |  |  |  |
| 26 | 382 | [Download](26/dataset.zip) |  |  |  |  |  |  |  |  |
| 27 | 66 | [Download](27/dataset.zip) |  |  |  |  |  |  |  |  |
| 28 | 61 | [Download](28/dataset.zip) |  |  |  |  |  |  |  |  |
| 29 | 108 | [Download](29/dataset.zip) |  |  |  |  |  |  |  |  |
| 30 | 273 | [Download](30/dataset.zip) |  |  |  |  |  |  |  |  |
| 31 | 78 | [Download](31/dataset.zip) |  |  |  |  |  |  |  |  |
| 32 | 49 | [Download](32/dataset.zip) |  |  |  |  |  |  |  |  |
| 33 | 46 | [Download](33/dataset.zip) |  |  |  |  |  |  |  |  |
| 34 | 346 | [Download](34/dataset.zip) |  |  |  |  |  |  |  |  |
| 35 | 123 | [Download](35/dataset.zip) |  |  |  |  |  |  |  |  |
| 36 | 327 | [Download](36/dataset.zip) |  |  |  |  |  |  |  |  |
| 37 | 32 | [Download](37/dataset.zip) |  |  |  |  |  |  |  |  |
| 38 | 50 | [Download](38/dataset.zip) |  |  |  |  |  |  |  |  |
| 39 | 38 | [Download](39/dataset.zip) |  |  |  |  |  |  |  |  |
| 40 | 1323 | [Download](40/dataset.zip) |  |  |  |  |  |  |  |  |
| 41 | 29 | [Download](41/dataset.zip) |  |  |  |  |  |  |  |  |
| 42 | 17 | [Download](42/dataset.zip) |  |  |  |  |  |  |  |  |
| 43 | 28 | [Download](43/dataset.zip) |  |  |  |  |  |  |  |  |
| 44 | 28 | [Download](44/dataset.zip) |  |  |  |  |  |  |  |  |
| 45 | 15 | [Download](45/dataset.zip) |  |  |  |  |  |  |  |  |
| 46 | 17 | [Download](46/dataset.zip) |  |  |  |  |  |  |  |  |
| 47 | 30 | [Download](47/dataset.zip) |  |  |  |  |  |  |  |  |
| 48 | 19 | [Download](48/dataset.zip) |  |  |  |  |  |  |  |  |
| 49 | 12 | [Download](49/dataset.zip) |  |  |  |  |  |  |  |  |
| 50 | 14 | [Download](50/dataset.zip) |  |  |  |  |  |  |  |  |
| 51 | 13 | [Download](51/dataset.zip) |  |  |  |  |  |  |  |  |
| 52 | 10 | [Download](52/dataset.zip) |  |  |  |  |  |  |  |  |
| 53 | 67 | [Download](53/dataset.zip) |  |  |  |  |  |  |  |  |
| 54 | 21 | [Download](54/dataset.zip) |  |  |  |  |  |  |  |  |
| 55 | 9 | [Download](55/dataset.zip) |  |  |  |  |  |  |  |  |
| 56 | 9 | [Download](56/dataset.zip) |  |  |  |  |  |  |  |  |
| 57 | 150 | [Download](57/dataset.zip) |  |  |  |  |  |  |  |  |
| 58 | 339 | [Download](58/dataset.zip) |  |  |  |  |  |  |  |  |
| 59 | 16 | [Download](59/dataset.zip) |  |  |  |  |  |  |  |  |
| 60 | 10 | [Download](60/dataset.zip) |  |  |  |  |  |  |  |  |
| 61 | 17 | [Download](61/dataset.zip) |  |  |  |  |  |  |  |  |
| 62 | 36 | [Download](62/dataset.zip) |  |  |  |  |  |  |  |  |
| 63 | 84 | [Download](63/dataset.zip) |  |  |  |  |  |  |  |  |
| 64 | 15 | [Download](64/dataset.zip) |  |  |  |  |  |  |  |  |
| 65 | 6 | [Download](65/dataset.zip) |  |  |  |  |  |  | N/A | N/A |
| 66 | 13 | [Download](66/dataset.zip) |  |  |  |  |  |  |  |  |
| 67 | 7 | [Download](67/dataset.zip) |  |  |  |  |  |  |  | N/A |
| 68 | 12 | [Download](68/dataset.zip) |  |  |  |  |  |  |  |  |
| noise | 135 | [Download](-1/dataset.zip) |  |  |  |  |  |  |  |  |
| BangumiBase/fumetsunoanatae | [
"size_categories:1K<n<10K",
"license:mit",
"art",
"region:us"
] | 2023-11-29T19:23:29+00:00 | {"license": "mit", "size_categories": ["1K<n<10K"], "tags": ["art"]} | 2023-11-29T23:50:58+00:00 | [] | [] | TAGS
#size_categories-1K<n<10K #license-mit #art #region-us
| Bangumi Image Base of Fumetsu No Anata E
========================================
This is the image base of bangumi Fumetsu no Anata e, we detected 70 characters, 7434 images in total. The full dataset is here.
Please note that these image bases are not guaranteed to be 100% cleaned, they may be noisy actual. If you intend to manually train models using this dataset, we recommend performing necessary preprocessing on the downloaded dataset to eliminate potential noisy samples (approximately 1% probability).
Here is the characters' preview:
| [] | [
"TAGS\n#size_categories-1K<n<10K #license-mit #art #region-us \n"
] | [
25
] | [
"passage: TAGS\n#size_categories-1K<n<10K #license-mit #art #region-us \n"
] |
18afea32e5f3206a608788d575ca871b90e1426a |
Offline RL benchmark datasets in highly stochastic domains introduced in the paper "One Risk to Rule Them All: A Risk-Sensitive Perspective on Model-Based Offline Reinforcement Learning", published at NeurIPS 2023.
For the accompanying code, please see the Github repo at [github.com/marc-rigter/1R2R](https://github.com/marc-rigter/1R2R). | marcrigter/1R2R-datasets | [
"license:mit",
"region:us"
] | 2023-11-29T19:29:16+00:00 | {"license": "mit", "pretty_name": "1R2R Datasets"} | 2023-11-29T20:02:46+00:00 | [] | [] | TAGS
#license-mit #region-us
|
Offline RL benchmark datasets in highly stochastic domains introduced in the paper "One Risk to Rule Them All: A Risk-Sensitive Perspective on Model-Based Offline Reinforcement Learning", published at NeurIPS 2023.
For the accompanying code, please see the Github repo at URL | [] | [
"TAGS\n#license-mit #region-us \n"
] | [
11
] | [
"passage: TAGS\n#license-mit #region-us \n"
] |
c1ed65922d21bd6224b4124dc451b027454433ad | # Dataset Card for "inference_pairs_clustered_2"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | gh1407/inference_pairs_clustered_2 | [
"region:us"
] | 2023-11-29T19:35:10+00:00 | {"dataset_info": {"features": [{"name": "original_string", "dtype": "string"}, {"name": "cause_split", "dtype": "string"}, {"name": "effect_split", "dtype": "string"}, {"name": "cause_summarized", "dtype": "string"}, {"name": "effect_summarized", "dtype": "string"}, {"name": "cause_summarized_chat_gpt", "dtype": "string"}, {"name": "effect_summarized_chat_gpt", "dtype": "string"}], "splits": [{"name": "train", "num_bytes": 1117606, "num_examples": 1302}], "download_size": 529961, "dataset_size": 1117606}} | 2023-11-29T19:36:51+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "inference_pairs_clustered_2"
More Information needed | [
"# Dataset Card for \"inference_pairs_clustered_2\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"inference_pairs_clustered_2\"\n\nMore Information needed"
] | [
6,
22
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"inference_pairs_clustered_2\"\n\nMore Information needed"
] |
dd58f1e2e605372a466a494bbbaefc6a92d5b1b2 |
# Bangumi Image Base of Kanata No Astra
This is the image base of bangumi Kanata no Astra, we detected 25 characters, 2286 images in total. The full dataset is [here](all.zip).
**Please note that these image bases are not guaranteed to be 100% cleaned, they may be noisy actual.** If you intend to manually train models using this dataset, we recommend performing necessary preprocessing on the downloaded dataset to eliminate potential noisy samples (approximately 1% probability).
Here is the characters' preview:
| # | Images | Download | Preview 1 | Preview 2 | Preview 3 | Preview 4 | Preview 5 | Preview 6 | Preview 7 | Preview 8 |
|:------|---------:|:---------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|
| 0 | 206 | [Download](0/dataset.zip) |  |  |  |  |  |  |  |  |
| 1 | 32 | [Download](1/dataset.zip) |  |  |  |  |  |  |  |  |
| 2 | 15 | [Download](2/dataset.zip) |  |  |  |  |  |  |  |  |
| 3 | 186 | [Download](3/dataset.zip) |  |  |  |  |  |  |  |  |
| 4 | 7 | [Download](4/dataset.zip) |  |  |  |  |  |  |  | N/A |
| 5 | 16 | [Download](5/dataset.zip) |  |  |  |  |  |  |  |  |
| 6 | 229 | [Download](6/dataset.zip) |  |  |  |  |  |  |  |  |
| 7 | 235 | [Download](7/dataset.zip) |  |  |  |  |  |  |  |  |
| 8 | 54 | [Download](8/dataset.zip) |  |  |  |  |  |  |  |  |
| 9 | 89 | [Download](9/dataset.zip) |  |  |  |  |  |  |  |  |
| 10 | 39 | [Download](10/dataset.zip) |  |  |  |  |  |  |  |  |
| 11 | 48 | [Download](11/dataset.zip) |  |  |  |  |  |  |  |  |
| 12 | 68 | [Download](12/dataset.zip) |  |  |  |  |  |  |  |  |
| 13 | 41 | [Download](13/dataset.zip) |  |  |  |  |  |  |  |  |
| 14 | 54 | [Download](14/dataset.zip) |  |  |  |  |  |  |  |  |
| 15 | 24 | [Download](15/dataset.zip) |  |  |  |  |  |  |  |  |
| 16 | 64 | [Download](16/dataset.zip) |  |  |  |  |  |  |  |  |
| 17 | 233 | [Download](17/dataset.zip) |  |  |  |  |  |  |  |  |
| 18 | 18 | [Download](18/dataset.zip) |  |  |  |  |  |  |  |  |
| 19 | 98 | [Download](19/dataset.zip) |  |  |  |  |  |  |  |  |
| 20 | 11 | [Download](20/dataset.zip) |  |  |  |  |  |  |  |  |
| 21 | 206 | [Download](21/dataset.zip) |  |  |  |  |  |  |  |  |
| 22 | 32 | [Download](22/dataset.zip) |  |  |  |  |  |  |  |  |
| 23 | 12 | [Download](23/dataset.zip) |  |  |  |  |  |  |  |  |
| noise | 269 | [Download](-1/dataset.zip) |  |  |  |  |  |  |  |  |
| BangumiBase/kanatanoastra | [
"size_categories:1K<n<10K",
"license:mit",
"art",
"region:us"
] | 2023-11-29T19:44:56+00:00 | {"license": "mit", "size_categories": ["1K<n<10K"], "tags": ["art"]} | 2023-11-29T20:47:47+00:00 | [] | [] | TAGS
#size_categories-1K<n<10K #license-mit #art #region-us
| Bangumi Image Base of Kanata No Astra
=====================================
This is the image base of bangumi Kanata no Astra, we detected 25 characters, 2286 images in total. The full dataset is here.
Please note that these image bases are not guaranteed to be 100% cleaned, they may be noisy actual. If you intend to manually train models using this dataset, we recommend performing necessary preprocessing on the downloaded dataset to eliminate potential noisy samples (approximately 1% probability).
Here is the characters' preview:
| [] | [
"TAGS\n#size_categories-1K<n<10K #license-mit #art #region-us \n"
] | [
25
] | [
"passage: TAGS\n#size_categories-1K<n<10K #license-mit #art #region-us \n"
] |
b5fe356695fcb77059f58e97531bd068dfb334eb | # Dataset Card for "step_by_step_diff_in_latex"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | AlFrauch/step_by_step_diff_in_latex | [
"region:us"
] | 2023-11-29T20:25:06+00:00 | {"dataset_info": {"features": [{"name": "function", "dtype": "string"}, {"name": "content", "dtype": "string"}], "splits": [{"name": "train", "num_bytes": 23674753, "num_examples": 6031}], "download_size": 3265633, "dataset_size": 23674753}} | 2023-11-29T20:41:55+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "step_by_step_diff_in_latex"
More Information needed | [
"# Dataset Card for \"step_by_step_diff_in_latex\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"step_by_step_diff_in_latex\"\n\nMore Information needed"
] | [
6,
22
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"step_by_step_diff_in_latex\"\n\nMore Information needed"
] |
c2f8a9302c7d4bbfad294c3c0db380025dcebfd4 | # Dataset Card for "Cityscape_3_classes"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | Arham-Imran/Cityscape_3_classes | [
"region:us"
] | 2023-11-29T20:37:52+00:00 | {"configs": [{"config_name": "default", "data_files": [{"split": "train", "path": "data/train-*"}, {"split": "val", "path": "data/val-*"}]}], "dataset_info": {"features": [{"name": "image", "dtype": "image"}, {"name": "label", "dtype": "image"}], "splits": [{"name": "train", "num_bytes": 6823742844.95, "num_examples": 2975}, {"name": "val", "num_bytes": 1185820665.0, "num_examples": 500}], "download_size": 8147610349, "dataset_size": 8009563509.95}} | 2023-11-29T22:20:52+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "Cityscape_3_classes"
More Information needed | [
"# Dataset Card for \"Cityscape_3_classes\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"Cityscape_3_classes\"\n\nMore Information needed"
] | [
6,
17
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"Cityscape_3_classes\"\n\nMore Information needed"
] |
bb98573873482ef94288cb92e4fe8baef9d2db08 | # Dataset Card for "terrain-jackal-utcustom-data-47-v1.0"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | sam1120/terrain-jackal-utcustom-data-47-v1.0 | [
"region:us"
] | 2023-11-29T20:51:38+00:00 | {"dataset_info": {"features": [{"name": "name", "dtype": "string"}, {"name": "pixel_values", "dtype": "image"}, {"name": "labels", "dtype": "image"}], "splits": [{"name": "train", "num_bytes": 131018340.0, "num_examples": 47}], "download_size": 38256231, "dataset_size": 131018340.0}} | 2023-11-29T23:21:15+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "terrain-jackal-utcustom-data-47-v1.0"
More Information needed | [
"# Dataset Card for \"terrain-jackal-utcustom-data-47-v1.0\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"terrain-jackal-utcustom-data-47-v1.0\"\n\nMore Information needed"
] | [
6,
25
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"terrain-jackal-utcustom-data-47-v1.0\"\n\nMore Information needed"
] |
9495cffecc005fb3ee9372b3d86af5b064d9d18a | # Dataset Card for "terrain-jackal-morning-344-v1.0"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | sam1120/terrain-jackal-morning-344-v1.0 | [
"region:us"
] | 2023-11-29T21:00:07+00:00 | {"dataset_info": {"features": [{"name": "name", "dtype": "string"}, {"name": "pixel_values", "dtype": "image"}, {"name": "labels", "dtype": "image"}], "splits": [{"name": "train", "num_bytes": 955653437.0, "num_examples": 344}], "download_size": 276803569, "dataset_size": 955653437.0}} | 2023-11-29T23:22:44+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "terrain-jackal-morning-344-v1.0"
More Information needed | [
"# Dataset Card for \"terrain-jackal-morning-344-v1.0\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"terrain-jackal-morning-344-v1.0\"\n\nMore Information needed"
] | [
6,
23
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"terrain-jackal-morning-344-v1.0\"\n\nMore Information needed"
] |
0644acddb5f49556d461d4083a3c0a079067050c |
# That's photos of my dog :) | Alphonsce/Fef_dataset | [
"region:us"
] | 2023-11-29T21:00:37+00:00 | {"dataset_info": {"features": [{"name": "image", "dtype": "image"}, {"name": "text", "dtype": "string"}], "splits": [{"name": "train", "num_bytes": 5469372.0, "num_examples": 21}], "download_size": 5470869, "dataset_size": 5469372.0}, "configs": [{"config_name": "default", "data_files": [{"split": "train", "path": "data/train-*"}]}]} | 2023-11-29T21:04:36+00:00 | [] | [] | TAGS
#region-us
|
# That's photos of my dog :) | [
"# That's photos of my dog :)"
] | [
"TAGS\n#region-us \n",
"# That's photos of my dog :)"
] | [
6,
9
] | [
"passage: TAGS\n#region-us \n# That's photos of my dog :)"
] |
95bdb94fc96f5c4dc94d93e7d923478279a029af | # Dataset Card for "neurosymbolic-contingency-bag1-v1.0"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | sam1120/neurosymbolic-contingency-bag1-v1.0 | [
"region:us"
] | 2023-11-29T21:05:54+00:00 | {"dataset_info": {"features": [{"name": "name", "dtype": "string"}, {"name": "pixel_values", "dtype": "image"}, {"name": "labels", "dtype": "image"}], "splits": [{"name": "train", "num_bytes": 2762220288.0, "num_examples": 174}], "download_size": 675963764, "dataset_size": 2762220288.0}} | 2023-11-29T21:15:42+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "neurosymbolic-contingency-bag1-v1.0"
More Information needed | [
"# Dataset Card for \"neurosymbolic-contingency-bag1-v1.0\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"neurosymbolic-contingency-bag1-v1.0\"\n\nMore Information needed"
] | [
6,
24
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"neurosymbolic-contingency-bag1-v1.0\"\n\nMore Information needed"
] |
acd366be1598b6b166dae1f82e409824432a7ede | # Dataset Card for "tokenized_t5_small_context_len_128"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | yardeny/tokenized_t5_small_context_len_128 | [
"region:us"
] | 2023-11-29T21:43:22+00:00 | {"dataset_info": {"features": [{"name": "input_ids", "sequence": "int32"}, {"name": "attention_mask", "sequence": "int8"}], "splits": [{"name": "train", "num_bytes": 11929196729, "num_examples": 80462898}], "download_size": 4372133615, "dataset_size": 11929196729}} | 2023-11-29T21:58:17+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "tokenized_t5_small_context_len_128"
More Information needed | [
"# Dataset Card for \"tokenized_t5_small_context_len_128\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"tokenized_t5_small_context_len_128\"\n\nMore Information needed"
] | [
6,
26
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"tokenized_t5_small_context_len_128\"\n\nMore Information needed"
] |
8211ee90662f4726f8a42e5d0115cc92c48548f4 | # Dataset Card for "tokenized_t5_small_context_len_64"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | yardeny/tokenized_t5_small_context_len_64 | [
"region:us"
] | 2023-11-29T21:44:36+00:00 | {"dataset_info": {"features": [{"name": "input_ids", "sequence": "int32"}, {"name": "attention_mask", "sequence": "int8"}], "splits": [{"name": "train", "num_bytes": 10163799114, "num_examples": 80462898}], "download_size": 3657002292, "dataset_size": 10163799114}} | 2023-11-29T21:52:29+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "tokenized_t5_small_context_len_64"
More Information needed | [
"# Dataset Card for \"tokenized_t5_small_context_len_64\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"tokenized_t5_small_context_len_64\"\n\nMore Information needed"
] | [
6,
26
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"tokenized_t5_small_context_len_64\"\n\nMore Information needed"
] |
a5608f75949d3ed42b147d852c38a3068c4cbd15 | מכיל כמה ספרים על שולחן ערוך אורח חיים:
* שולחן ערוך
* מגן אברהם
* ט"ז
* עטרת זקנים
* שערי תשובה
* באר היטב
* משנה ברורה
* ביאור הלכה | sivan22/orach-chaim | [
"region:us"
] | 2023-11-29T21:48:46+00:00 | {"dataset_info": {"features": [{"name": "Unnamed: 0", "dtype": "int64"}, {"name": "bookname", "dtype": "string"}, {"name": "siman", "dtype": "string"}, {"name": "sek", "dtype": "string"}, {"name": "text", "dtype": "string"}, {"name": "seif", "dtype": "string"}, {"name": "topic", "dtype": "string"}], "splits": [{"name": "train", "num_bytes": 24562239, "num_examples": 42608}], "download_size": 10932463, "dataset_size": 24562239}, "configs": [{"config_name": "default", "data_files": [{"split": "train", "path": "data/train-*"}]}]} | 2023-12-03T10:56:11+00:00 | [] | [] | TAGS
#region-us
| מכיל כמה ספרים על שולחן ערוך אורח חיים:
* שולחן ערוך
* מגן אברהם
* ט"ז
* עטרת זקנים
* שערי תשובה
* באר היטב
* משנה ברורה
* ביאור הלכה | [] | [
"TAGS\n#region-us \n"
] | [
6
] | [
"passage: TAGS\n#region-us \n"
] |
fb0a5d7d68cdd10d49eb7337e76fe19258ef3a5a | # Dataset Card for "processed_t5_small_context_len_64"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | yardeny/processed_t5_small_context_len_64 | [
"region:us"
] | 2023-11-29T21:57:12+00:00 | {"dataset_info": {"features": [{"name": "input_ids", "sequence": "int32"}, {"name": "attention_mask", "sequence": "int8"}], "splits": [{"name": "train", "num_bytes": 9745169624.0, "num_examples": 29710883}], "download_size": 3781295100, "dataset_size": 9745169624.0}} | 2023-11-29T22:10:40+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "processed_t5_small_context_len_64"
More Information needed | [
"# Dataset Card for \"processed_t5_small_context_len_64\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"processed_t5_small_context_len_64\"\n\nMore Information needed"
] | [
6,
25
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"processed_t5_small_context_len_64\"\n\nMore Information needed"
] |
4ed694d6f1e36417096205a0a36c93c1c92c3a45 | # Dataset Card for "processed_t5_small_context_len_128"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | yardeny/processed_t5_small_context_len_128 | [
"region:us"
] | 2023-11-29T22:03:49+00:00 | {"dataset_info": {"features": [{"name": "input_ids", "sequence": "int32"}, {"name": "attention_mask", "sequence": "int8"}], "splits": [{"name": "train", "num_bytes": 11400746112.0, "num_examples": 17593744}], "download_size": 4372291284, "dataset_size": 11400746112.0}} | 2023-11-29T22:21:51+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "processed_t5_small_context_len_128"
More Information needed | [
"# Dataset Card for \"processed_t5_small_context_len_128\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"processed_t5_small_context_len_128\"\n\nMore Information needed"
] | [
6,
25
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"processed_t5_small_context_len_128\"\n\nMore Information needed"
] |
cfbd0de05b3b513bc27c1a99a34687da61e76c13 |
# Dataset Card for Evaluation run of argilla/notus-7b-v1
## Dataset Description
- **Homepage:**
- **Repository:** https://huggingface.co/argilla/notus-7b-v1
- **Paper:**
- **Leaderboard:** https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard
- **Point of Contact:** [email protected]
### Dataset Summary
Dataset automatically created during the evaluation run of model [argilla/notus-7b-v1](https://huggingface.co/argilla/notus-7b-v1) on the [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard).
The dataset is composed of 64 configuration, each one coresponding to one of the evaluated task.
The dataset has been created from 2 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always pointing to the latest results.
An additional configuration "results" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)).
To load the details from a run, you can for instance do the following:
```python
from datasets import load_dataset
data = load_dataset("open-llm-leaderboard/details_argilla__notus-7b-v1",
"harness_winogrande_5",
split="train")
```
## Latest results
These are the [latest results from run 2023-12-04T17:15:53.519887](https://huggingface.co/datasets/open-llm-leaderboard/details_argilla__notus-7b-v1/blob/main/results_2023-12-04T17-15-53.519887.json)(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the "latest" split for each eval):
```python
{
"all": {
"acc": 0.6284345225205253,
"acc_stderr": 0.03266688541458245,
"acc_norm": 0.6343199967908271,
"acc_norm_stderr": 0.03333546965424883,
"mc1": 0.36474908200734396,
"mc1_stderr": 0.01685096106172012,
"mc2": 0.5434993224846835,
"mc2_stderr": 0.01537768281733017
},
"harness|arc:challenge|25": {
"acc": 0.6092150170648464,
"acc_stderr": 0.01425856388051378,
"acc_norm": 0.6459044368600683,
"acc_norm_stderr": 0.01397545412275656
},
"harness|hellaswag|10": {
"acc": 0.6533559051981677,
"acc_stderr": 0.004749286071559562,
"acc_norm": 0.8483369846644094,
"acc_norm_stderr": 0.0035796087435066106
},
"harness|hendrycksTest-abstract_algebra|5": {
"acc": 0.29,
"acc_stderr": 0.045604802157206845,
"acc_norm": 0.29,
"acc_norm_stderr": 0.045604802157206845
},
"harness|hendrycksTest-anatomy|5": {
"acc": 0.6074074074074074,
"acc_stderr": 0.0421850621536888,
"acc_norm": 0.6074074074074074,
"acc_norm_stderr": 0.0421850621536888
},
"harness|hendrycksTest-astronomy|5": {
"acc": 0.631578947368421,
"acc_stderr": 0.03925523381052932,
"acc_norm": 0.631578947368421,
"acc_norm_stderr": 0.03925523381052932
},
"harness|hendrycksTest-business_ethics|5": {
"acc": 0.58,
"acc_stderr": 0.049604496374885836,
"acc_norm": 0.58,
"acc_norm_stderr": 0.049604496374885836
},
"harness|hendrycksTest-clinical_knowledge|5": {
"acc": 0.6981132075471698,
"acc_stderr": 0.02825420034443866,
"acc_norm": 0.6981132075471698,
"acc_norm_stderr": 0.02825420034443866
},
"harness|hendrycksTest-college_biology|5": {
"acc": 0.7361111111111112,
"acc_stderr": 0.03685651095897532,
"acc_norm": 0.7361111111111112,
"acc_norm_stderr": 0.03685651095897532
},
"harness|hendrycksTest-college_chemistry|5": {
"acc": 0.47,
"acc_stderr": 0.050161355804659205,
"acc_norm": 0.47,
"acc_norm_stderr": 0.050161355804659205
},
"harness|hendrycksTest-college_computer_science|5": {
"acc": 0.5,
"acc_stderr": 0.050251890762960605,
"acc_norm": 0.5,
"acc_norm_stderr": 0.050251890762960605
},
"harness|hendrycksTest-college_mathematics|5": {
"acc": 0.38,
"acc_stderr": 0.04878317312145633,
"acc_norm": 0.38,
"acc_norm_stderr": 0.04878317312145633
},
"harness|hendrycksTest-college_medicine|5": {
"acc": 0.6473988439306358,
"acc_stderr": 0.03643037168958548,
"acc_norm": 0.6473988439306358,
"acc_norm_stderr": 0.03643037168958548
},
"harness|hendrycksTest-college_physics|5": {
"acc": 0.38235294117647056,
"acc_stderr": 0.04835503696107223,
"acc_norm": 0.38235294117647056,
"acc_norm_stderr": 0.04835503696107223
},
"harness|hendrycksTest-computer_security|5": {
"acc": 0.8,
"acc_stderr": 0.04020151261036846,
"acc_norm": 0.8,
"acc_norm_stderr": 0.04020151261036846
},
"harness|hendrycksTest-conceptual_physics|5": {
"acc": 0.5276595744680851,
"acc_stderr": 0.03263597118409769,
"acc_norm": 0.5276595744680851,
"acc_norm_stderr": 0.03263597118409769
},
"harness|hendrycksTest-econometrics|5": {
"acc": 0.4473684210526316,
"acc_stderr": 0.046774730044911984,
"acc_norm": 0.4473684210526316,
"acc_norm_stderr": 0.046774730044911984
},
"harness|hendrycksTest-electrical_engineering|5": {
"acc": 0.5517241379310345,
"acc_stderr": 0.04144311810878151,
"acc_norm": 0.5517241379310345,
"acc_norm_stderr": 0.04144311810878151
},
"harness|hendrycksTest-elementary_mathematics|5": {
"acc": 0.41534391534391535,
"acc_stderr": 0.025379524910778405,
"acc_norm": 0.41534391534391535,
"acc_norm_stderr": 0.025379524910778405
},
"harness|hendrycksTest-formal_logic|5": {
"acc": 0.3968253968253968,
"acc_stderr": 0.04375888492727061,
"acc_norm": 0.3968253968253968,
"acc_norm_stderr": 0.04375888492727061
},
"harness|hendrycksTest-global_facts|5": {
"acc": 0.41,
"acc_stderr": 0.04943110704237102,
"acc_norm": 0.41,
"acc_norm_stderr": 0.04943110704237102
},
"harness|hendrycksTest-high_school_biology|5": {
"acc": 0.7451612903225806,
"acc_stderr": 0.024790118459332208,
"acc_norm": 0.7451612903225806,
"acc_norm_stderr": 0.024790118459332208
},
"harness|hendrycksTest-high_school_chemistry|5": {
"acc": 0.5172413793103449,
"acc_stderr": 0.035158955511656986,
"acc_norm": 0.5172413793103449,
"acc_norm_stderr": 0.035158955511656986
},
"harness|hendrycksTest-high_school_computer_science|5": {
"acc": 0.68,
"acc_stderr": 0.04688261722621504,
"acc_norm": 0.68,
"acc_norm_stderr": 0.04688261722621504
},
"harness|hendrycksTest-high_school_european_history|5": {
"acc": 0.7757575757575758,
"acc_stderr": 0.032568666616811015,
"acc_norm": 0.7757575757575758,
"acc_norm_stderr": 0.032568666616811015
},
"harness|hendrycksTest-high_school_geography|5": {
"acc": 0.7727272727272727,
"acc_stderr": 0.029857515673386424,
"acc_norm": 0.7727272727272727,
"acc_norm_stderr": 0.029857515673386424
},
"harness|hendrycksTest-high_school_government_and_politics|5": {
"acc": 0.8756476683937824,
"acc_stderr": 0.023814477086593552,
"acc_norm": 0.8756476683937824,
"acc_norm_stderr": 0.023814477086593552
},
"harness|hendrycksTest-high_school_macroeconomics|5": {
"acc": 0.6358974358974359,
"acc_stderr": 0.024396672985094764,
"acc_norm": 0.6358974358974359,
"acc_norm_stderr": 0.024396672985094764
},
"harness|hendrycksTest-high_school_mathematics|5": {
"acc": 0.36666666666666664,
"acc_stderr": 0.02938162072646507,
"acc_norm": 0.36666666666666664,
"acc_norm_stderr": 0.02938162072646507
},
"harness|hendrycksTest-high_school_microeconomics|5": {
"acc": 0.6932773109243697,
"acc_stderr": 0.029953823891887034,
"acc_norm": 0.6932773109243697,
"acc_norm_stderr": 0.029953823891887034
},
"harness|hendrycksTest-high_school_physics|5": {
"acc": 0.31788079470198677,
"acc_stderr": 0.038020397601079024,
"acc_norm": 0.31788079470198677,
"acc_norm_stderr": 0.038020397601079024
},
"harness|hendrycksTest-high_school_psychology|5": {
"acc": 0.8091743119266055,
"acc_stderr": 0.016847676400091122,
"acc_norm": 0.8091743119266055,
"acc_norm_stderr": 0.016847676400091122
},
"harness|hendrycksTest-high_school_statistics|5": {
"acc": 0.5324074074074074,
"acc_stderr": 0.03402801581358966,
"acc_norm": 0.5324074074074074,
"acc_norm_stderr": 0.03402801581358966
},
"harness|hendrycksTest-high_school_us_history|5": {
"acc": 0.803921568627451,
"acc_stderr": 0.027865942286639325,
"acc_norm": 0.803921568627451,
"acc_norm_stderr": 0.027865942286639325
},
"harness|hendrycksTest-high_school_world_history|5": {
"acc": 0.7805907172995781,
"acc_stderr": 0.026939106581553945,
"acc_norm": 0.7805907172995781,
"acc_norm_stderr": 0.026939106581553945
},
"harness|hendrycksTest-human_aging|5": {
"acc": 0.6457399103139013,
"acc_stderr": 0.032100621541349864,
"acc_norm": 0.6457399103139013,
"acc_norm_stderr": 0.032100621541349864
},
"harness|hendrycksTest-human_sexuality|5": {
"acc": 0.7175572519083969,
"acc_stderr": 0.03948406125768361,
"acc_norm": 0.7175572519083969,
"acc_norm_stderr": 0.03948406125768361
},
"harness|hendrycksTest-international_law|5": {
"acc": 0.7603305785123967,
"acc_stderr": 0.03896878985070416,
"acc_norm": 0.7603305785123967,
"acc_norm_stderr": 0.03896878985070416
},
"harness|hendrycksTest-jurisprudence|5": {
"acc": 0.7222222222222222,
"acc_stderr": 0.04330043749650742,
"acc_norm": 0.7222222222222222,
"acc_norm_stderr": 0.04330043749650742
},
"harness|hendrycksTest-logical_fallacies|5": {
"acc": 0.7177914110429447,
"acc_stderr": 0.03536117886664743,
"acc_norm": 0.7177914110429447,
"acc_norm_stderr": 0.03536117886664743
},
"harness|hendrycksTest-machine_learning|5": {
"acc": 0.5357142857142857,
"acc_stderr": 0.04733667890053756,
"acc_norm": 0.5357142857142857,
"acc_norm_stderr": 0.04733667890053756
},
"harness|hendrycksTest-management|5": {
"acc": 0.7669902912621359,
"acc_stderr": 0.04185832598928315,
"acc_norm": 0.7669902912621359,
"acc_norm_stderr": 0.04185832598928315
},
"harness|hendrycksTest-marketing|5": {
"acc": 0.8461538461538461,
"acc_stderr": 0.023636873317489277,
"acc_norm": 0.8461538461538461,
"acc_norm_stderr": 0.023636873317489277
},
"harness|hendrycksTest-medical_genetics|5": {
"acc": 0.75,
"acc_stderr": 0.04351941398892446,
"acc_norm": 0.75,
"acc_norm_stderr": 0.04351941398892446
},
"harness|hendrycksTest-miscellaneous|5": {
"acc": 0.8109833971902938,
"acc_stderr": 0.014000791294406999,
"acc_norm": 0.8109833971902938,
"acc_norm_stderr": 0.014000791294406999
},
"harness|hendrycksTest-moral_disputes|5": {
"acc": 0.684971098265896,
"acc_stderr": 0.0250093137900697,
"acc_norm": 0.684971098265896,
"acc_norm_stderr": 0.0250093137900697
},
"harness|hendrycksTest-moral_scenarios|5": {
"acc": 0.45139664804469276,
"acc_stderr": 0.016643307372315872,
"acc_norm": 0.45139664804469276,
"acc_norm_stderr": 0.016643307372315872
},
"harness|hendrycksTest-nutrition|5": {
"acc": 0.7026143790849673,
"acc_stderr": 0.026173908506718576,
"acc_norm": 0.7026143790849673,
"acc_norm_stderr": 0.026173908506718576
},
"harness|hendrycksTest-philosophy|5": {
"acc": 0.6945337620578779,
"acc_stderr": 0.026160584450140453,
"acc_norm": 0.6945337620578779,
"acc_norm_stderr": 0.026160584450140453
},
"harness|hendrycksTest-prehistory|5": {
"acc": 0.7006172839506173,
"acc_stderr": 0.025483115601195455,
"acc_norm": 0.7006172839506173,
"acc_norm_stderr": 0.025483115601195455
},
"harness|hendrycksTest-professional_accounting|5": {
"acc": 0.46099290780141844,
"acc_stderr": 0.02973659252642444,
"acc_norm": 0.46099290780141844,
"acc_norm_stderr": 0.02973659252642444
},
"harness|hendrycksTest-professional_law|5": {
"acc": 0.4367666232073012,
"acc_stderr": 0.012667701919603662,
"acc_norm": 0.4367666232073012,
"acc_norm_stderr": 0.012667701919603662
},
"harness|hendrycksTest-professional_medicine|5": {
"acc": 0.6764705882352942,
"acc_stderr": 0.02841820861940676,
"acc_norm": 0.6764705882352942,
"acc_norm_stderr": 0.02841820861940676
},
"harness|hendrycksTest-professional_psychology|5": {
"acc": 0.6437908496732027,
"acc_stderr": 0.019373332420724504,
"acc_norm": 0.6437908496732027,
"acc_norm_stderr": 0.019373332420724504
},
"harness|hendrycksTest-public_relations|5": {
"acc": 0.7090909090909091,
"acc_stderr": 0.04350271442923243,
"acc_norm": 0.7090909090909091,
"acc_norm_stderr": 0.04350271442923243
},
"harness|hendrycksTest-security_studies|5": {
"acc": 0.6979591836734694,
"acc_stderr": 0.029393609319879804,
"acc_norm": 0.6979591836734694,
"acc_norm_stderr": 0.029393609319879804
},
"harness|hendrycksTest-sociology|5": {
"acc": 0.8059701492537313,
"acc_stderr": 0.0279626776047689,
"acc_norm": 0.8059701492537313,
"acc_norm_stderr": 0.0279626776047689
},
"harness|hendrycksTest-us_foreign_policy|5": {
"acc": 0.83,
"acc_stderr": 0.0377525168068637,
"acc_norm": 0.83,
"acc_norm_stderr": 0.0377525168068637
},
"harness|hendrycksTest-virology|5": {
"acc": 0.5240963855421686,
"acc_stderr": 0.03887971849597264,
"acc_norm": 0.5240963855421686,
"acc_norm_stderr": 0.03887971849597264
},
"harness|hendrycksTest-world_religions|5": {
"acc": 0.8596491228070176,
"acc_stderr": 0.0266405825391332,
"acc_norm": 0.8596491228070176,
"acc_norm_stderr": 0.0266405825391332
},
"harness|truthfulqa:mc|0": {
"mc1": 0.36474908200734396,
"mc1_stderr": 0.01685096106172012,
"mc2": 0.5434993224846835,
"mc2_stderr": 0.01537768281733017
},
"harness|winogrande|5": {
"acc": 0.7955801104972375,
"acc_stderr": 0.011334090612597207
},
"harness|gsm8k|5": {
"acc": 0.3457164518574678,
"acc_stderr": 0.013100422990441573
}
}
```
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
[More Information Needed]
## Dataset Structure
### Data Instances
[More Information Needed]
### Data Fields
[More Information Needed]
### Data Splits
[More Information Needed]
## Dataset Creation
### Curation Rationale
[More Information Needed]
### Source Data
#### Initial Data Collection and Normalization
[More Information Needed]
#### Who are the source language producers?
[More Information Needed]
### Annotations
#### Annotation process
[More Information Needed]
#### Who are the annotators?
[More Information Needed]
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
[More Information Needed]
### Licensing Information
[More Information Needed]
### Citation Information
[More Information Needed]
### Contributions
[More Information Needed] | open-llm-leaderboard/details_argilla__notus-7b-v1 | [
"region:us"
] | 2023-11-29T22:19:52+00:00 | {"pretty_name": "Evaluation run of argilla/notus-7b-v1", "dataset_summary": "Dataset automatically created during the evaluation run of model [argilla/notus-7b-v1](https://huggingface.co/argilla/notus-7b-v1) on the [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard).\n\nThe dataset is composed of 64 configuration, each one coresponding to one of the evaluated task.\n\nThe dataset has been created from 2 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The \"train\" split is always pointing to the latest results.\n\nAn additional configuration \"results\" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)).\n\nTo load the details from a run, you can for instance do the following:\n```python\nfrom datasets import load_dataset\ndata = load_dataset(\"open-llm-leaderboard/details_argilla__notus-7b-v1\",\n\t\"harness_winogrande_5\",\n\tsplit=\"train\")\n```\n\n## Latest results\n\nThese are the [latest results from run 2023-12-04T17:15:53.519887](https://huggingface.co/datasets/open-llm-leaderboard/details_argilla__notus-7b-v1/blob/main/results_2023-12-04T17-15-53.519887.json)(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the \"latest\" split for each eval):\n\n```python\n{\n \"all\": {\n \"acc\": 0.6284345225205253,\n \"acc_stderr\": 0.03266688541458245,\n \"acc_norm\": 0.6343199967908271,\n \"acc_norm_stderr\": 0.03333546965424883,\n \"mc1\": 0.36474908200734396,\n \"mc1_stderr\": 0.01685096106172012,\n \"mc2\": 0.5434993224846835,\n \"mc2_stderr\": 0.01537768281733017\n },\n \"harness|arc:challenge|25\": {\n \"acc\": 0.6092150170648464,\n \"acc_stderr\": 0.01425856388051378,\n \"acc_norm\": 0.6459044368600683,\n \"acc_norm_stderr\": 0.01397545412275656\n },\n \"harness|hellaswag|10\": {\n \"acc\": 0.6533559051981677,\n \"acc_stderr\": 0.004749286071559562,\n \"acc_norm\": 0.8483369846644094,\n \"acc_norm_stderr\": 0.0035796087435066106\n },\n \"harness|hendrycksTest-abstract_algebra|5\": {\n \"acc\": 0.29,\n \"acc_stderr\": 0.045604802157206845,\n \"acc_norm\": 0.29,\n \"acc_norm_stderr\": 0.045604802157206845\n },\n \"harness|hendrycksTest-anatomy|5\": {\n \"acc\": 0.6074074074074074,\n \"acc_stderr\": 0.0421850621536888,\n \"acc_norm\": 0.6074074074074074,\n \"acc_norm_stderr\": 0.0421850621536888\n },\n \"harness|hendrycksTest-astronomy|5\": {\n \"acc\": 0.631578947368421,\n \"acc_stderr\": 0.03925523381052932,\n \"acc_norm\": 0.631578947368421,\n \"acc_norm_stderr\": 0.03925523381052932\n },\n \"harness|hendrycksTest-business_ethics|5\": {\n \"acc\": 0.58,\n \"acc_stderr\": 0.049604496374885836,\n \"acc_norm\": 0.58,\n \"acc_norm_stderr\": 0.049604496374885836\n },\n \"harness|hendrycksTest-clinical_knowledge|5\": {\n \"acc\": 0.6981132075471698,\n \"acc_stderr\": 0.02825420034443866,\n \"acc_norm\": 0.6981132075471698,\n \"acc_norm_stderr\": 0.02825420034443866\n },\n \"harness|hendrycksTest-college_biology|5\": {\n \"acc\": 0.7361111111111112,\n \"acc_stderr\": 0.03685651095897532,\n \"acc_norm\": 0.7361111111111112,\n \"acc_norm_stderr\": 0.03685651095897532\n },\n \"harness|hendrycksTest-college_chemistry|5\": {\n \"acc\": 0.47,\n \"acc_stderr\": 0.050161355804659205,\n \"acc_norm\": 0.47,\n \"acc_norm_stderr\": 0.050161355804659205\n },\n \"harness|hendrycksTest-college_computer_science|5\": {\n \"acc\": 0.5,\n \"acc_stderr\": 0.050251890762960605,\n \"acc_norm\": 0.5,\n \"acc_norm_stderr\": 0.050251890762960605\n },\n \"harness|hendrycksTest-college_mathematics|5\": {\n \"acc\": 0.38,\n \"acc_stderr\": 0.04878317312145633,\n \"acc_norm\": 0.38,\n \"acc_norm_stderr\": 0.04878317312145633\n },\n \"harness|hendrycksTest-college_medicine|5\": {\n \"acc\": 0.6473988439306358,\n \"acc_stderr\": 0.03643037168958548,\n \"acc_norm\": 0.6473988439306358,\n \"acc_norm_stderr\": 0.03643037168958548\n },\n \"harness|hendrycksTest-college_physics|5\": {\n \"acc\": 0.38235294117647056,\n \"acc_stderr\": 0.04835503696107223,\n \"acc_norm\": 0.38235294117647056,\n \"acc_norm_stderr\": 0.04835503696107223\n },\n \"harness|hendrycksTest-computer_security|5\": {\n \"acc\": 0.8,\n \"acc_stderr\": 0.04020151261036846,\n \"acc_norm\": 0.8,\n \"acc_norm_stderr\": 0.04020151261036846\n },\n \"harness|hendrycksTest-conceptual_physics|5\": {\n \"acc\": 0.5276595744680851,\n \"acc_stderr\": 0.03263597118409769,\n \"acc_norm\": 0.5276595744680851,\n \"acc_norm_stderr\": 0.03263597118409769\n },\n \"harness|hendrycksTest-econometrics|5\": {\n \"acc\": 0.4473684210526316,\n \"acc_stderr\": 0.046774730044911984,\n \"acc_norm\": 0.4473684210526316,\n \"acc_norm_stderr\": 0.046774730044911984\n },\n \"harness|hendrycksTest-electrical_engineering|5\": {\n \"acc\": 0.5517241379310345,\n \"acc_stderr\": 0.04144311810878151,\n \"acc_norm\": 0.5517241379310345,\n \"acc_norm_stderr\": 0.04144311810878151\n },\n \"harness|hendrycksTest-elementary_mathematics|5\": {\n \"acc\": 0.41534391534391535,\n \"acc_stderr\": 0.025379524910778405,\n \"acc_norm\": 0.41534391534391535,\n \"acc_norm_stderr\": 0.025379524910778405\n },\n \"harness|hendrycksTest-formal_logic|5\": {\n \"acc\": 0.3968253968253968,\n \"acc_stderr\": 0.04375888492727061,\n \"acc_norm\": 0.3968253968253968,\n \"acc_norm_stderr\": 0.04375888492727061\n },\n \"harness|hendrycksTest-global_facts|5\": {\n \"acc\": 0.41,\n \"acc_stderr\": 0.04943110704237102,\n \"acc_norm\": 0.41,\n \"acc_norm_stderr\": 0.04943110704237102\n },\n \"harness|hendrycksTest-high_school_biology|5\": {\n \"acc\": 0.7451612903225806,\n \"acc_stderr\": 0.024790118459332208,\n \"acc_norm\": 0.7451612903225806,\n \"acc_norm_stderr\": 0.024790118459332208\n },\n \"harness|hendrycksTest-high_school_chemistry|5\": {\n \"acc\": 0.5172413793103449,\n \"acc_stderr\": 0.035158955511656986,\n \"acc_norm\": 0.5172413793103449,\n \"acc_norm_stderr\": 0.035158955511656986\n },\n \"harness|hendrycksTest-high_school_computer_science|5\": {\n \"acc\": 0.68,\n \"acc_stderr\": 0.04688261722621504,\n \"acc_norm\": 0.68,\n \"acc_norm_stderr\": 0.04688261722621504\n },\n \"harness|hendrycksTest-high_school_european_history|5\": {\n \"acc\": 0.7757575757575758,\n \"acc_stderr\": 0.032568666616811015,\n \"acc_norm\": 0.7757575757575758,\n \"acc_norm_stderr\": 0.032568666616811015\n },\n \"harness|hendrycksTest-high_school_geography|5\": {\n \"acc\": 0.7727272727272727,\n \"acc_stderr\": 0.029857515673386424,\n \"acc_norm\": 0.7727272727272727,\n \"acc_norm_stderr\": 0.029857515673386424\n },\n \"harness|hendrycksTest-high_school_government_and_politics|5\": {\n \"acc\": 0.8756476683937824,\n \"acc_stderr\": 0.023814477086593552,\n \"acc_norm\": 0.8756476683937824,\n \"acc_norm_stderr\": 0.023814477086593552\n },\n \"harness|hendrycksTest-high_school_macroeconomics|5\": {\n \"acc\": 0.6358974358974359,\n \"acc_stderr\": 0.024396672985094764,\n \"acc_norm\": 0.6358974358974359,\n \"acc_norm_stderr\": 0.024396672985094764\n },\n \"harness|hendrycksTest-high_school_mathematics|5\": {\n \"acc\": 0.36666666666666664,\n \"acc_stderr\": 0.02938162072646507,\n \"acc_norm\": 0.36666666666666664,\n \"acc_norm_stderr\": 0.02938162072646507\n },\n \"harness|hendrycksTest-high_school_microeconomics|5\": {\n \"acc\": 0.6932773109243697,\n \"acc_stderr\": 0.029953823891887034,\n \"acc_norm\": 0.6932773109243697,\n \"acc_norm_stderr\": 0.029953823891887034\n },\n \"harness|hendrycksTest-high_school_physics|5\": {\n \"acc\": 0.31788079470198677,\n \"acc_stderr\": 0.038020397601079024,\n \"acc_norm\": 0.31788079470198677,\n \"acc_norm_stderr\": 0.038020397601079024\n },\n \"harness|hendrycksTest-high_school_psychology|5\": {\n \"acc\": 0.8091743119266055,\n \"acc_stderr\": 0.016847676400091122,\n \"acc_norm\": 0.8091743119266055,\n \"acc_norm_stderr\": 0.016847676400091122\n },\n \"harness|hendrycksTest-high_school_statistics|5\": {\n \"acc\": 0.5324074074074074,\n \"acc_stderr\": 0.03402801581358966,\n \"acc_norm\": 0.5324074074074074,\n \"acc_norm_stderr\": 0.03402801581358966\n },\n \"harness|hendrycksTest-high_school_us_history|5\": {\n \"acc\": 0.803921568627451,\n \"acc_stderr\": 0.027865942286639325,\n \"acc_norm\": 0.803921568627451,\n \"acc_norm_stderr\": 0.027865942286639325\n },\n \"harness|hendrycksTest-high_school_world_history|5\": {\n \"acc\": 0.7805907172995781,\n \"acc_stderr\": 0.026939106581553945,\n \"acc_norm\": 0.7805907172995781,\n \"acc_norm_stderr\": 0.026939106581553945\n },\n \"harness|hendrycksTest-human_aging|5\": {\n \"acc\": 0.6457399103139013,\n \"acc_stderr\": 0.032100621541349864,\n \"acc_norm\": 0.6457399103139013,\n \"acc_norm_stderr\": 0.032100621541349864\n },\n \"harness|hendrycksTest-human_sexuality|5\": {\n \"acc\": 0.7175572519083969,\n \"acc_stderr\": 0.03948406125768361,\n \"acc_norm\": 0.7175572519083969,\n \"acc_norm_stderr\": 0.03948406125768361\n },\n \"harness|hendrycksTest-international_law|5\": {\n \"acc\": 0.7603305785123967,\n \"acc_stderr\": 0.03896878985070416,\n \"acc_norm\": 0.7603305785123967,\n \"acc_norm_stderr\": 0.03896878985070416\n },\n \"harness|hendrycksTest-jurisprudence|5\": {\n \"acc\": 0.7222222222222222,\n \"acc_stderr\": 0.04330043749650742,\n \"acc_norm\": 0.7222222222222222,\n \"acc_norm_stderr\": 0.04330043749650742\n },\n \"harness|hendrycksTest-logical_fallacies|5\": {\n \"acc\": 0.7177914110429447,\n \"acc_stderr\": 0.03536117886664743,\n \"acc_norm\": 0.7177914110429447,\n \"acc_norm_stderr\": 0.03536117886664743\n },\n \"harness|hendrycksTest-machine_learning|5\": {\n \"acc\": 0.5357142857142857,\n \"acc_stderr\": 0.04733667890053756,\n \"acc_norm\": 0.5357142857142857,\n \"acc_norm_stderr\": 0.04733667890053756\n },\n \"harness|hendrycksTest-management|5\": {\n \"acc\": 0.7669902912621359,\n \"acc_stderr\": 0.04185832598928315,\n \"acc_norm\": 0.7669902912621359,\n \"acc_norm_stderr\": 0.04185832598928315\n },\n \"harness|hendrycksTest-marketing|5\": {\n \"acc\": 0.8461538461538461,\n \"acc_stderr\": 0.023636873317489277,\n \"acc_norm\": 0.8461538461538461,\n \"acc_norm_stderr\": 0.023636873317489277\n },\n \"harness|hendrycksTest-medical_genetics|5\": {\n \"acc\": 0.75,\n \"acc_stderr\": 0.04351941398892446,\n \"acc_norm\": 0.75,\n \"acc_norm_stderr\": 0.04351941398892446\n },\n \"harness|hendrycksTest-miscellaneous|5\": {\n \"acc\": 0.8109833971902938,\n \"acc_stderr\": 0.014000791294406999,\n \"acc_norm\": 0.8109833971902938,\n \"acc_norm_stderr\": 0.014000791294406999\n },\n \"harness|hendrycksTest-moral_disputes|5\": {\n \"acc\": 0.684971098265896,\n \"acc_stderr\": 0.0250093137900697,\n \"acc_norm\": 0.684971098265896,\n \"acc_norm_stderr\": 0.0250093137900697\n },\n \"harness|hendrycksTest-moral_scenarios|5\": {\n \"acc\": 0.45139664804469276,\n \"acc_stderr\": 0.016643307372315872,\n \"acc_norm\": 0.45139664804469276,\n \"acc_norm_stderr\": 0.016643307372315872\n },\n \"harness|hendrycksTest-nutrition|5\": {\n \"acc\": 0.7026143790849673,\n \"acc_stderr\": 0.026173908506718576,\n \"acc_norm\": 0.7026143790849673,\n \"acc_norm_stderr\": 0.026173908506718576\n },\n \"harness|hendrycksTest-philosophy|5\": {\n \"acc\": 0.6945337620578779,\n \"acc_stderr\": 0.026160584450140453,\n \"acc_norm\": 0.6945337620578779,\n \"acc_norm_stderr\": 0.026160584450140453\n },\n \"harness|hendrycksTest-prehistory|5\": {\n \"acc\": 0.7006172839506173,\n \"acc_stderr\": 0.025483115601195455,\n \"acc_norm\": 0.7006172839506173,\n \"acc_norm_stderr\": 0.025483115601195455\n },\n \"harness|hendrycksTest-professional_accounting|5\": {\n \"acc\": 0.46099290780141844,\n \"acc_stderr\": 0.02973659252642444,\n \"acc_norm\": 0.46099290780141844,\n \"acc_norm_stderr\": 0.02973659252642444\n },\n \"harness|hendrycksTest-professional_law|5\": {\n \"acc\": 0.4367666232073012,\n \"acc_stderr\": 0.012667701919603662,\n \"acc_norm\": 0.4367666232073012,\n \"acc_norm_stderr\": 0.012667701919603662\n },\n \"harness|hendrycksTest-professional_medicine|5\": {\n \"acc\": 0.6764705882352942,\n \"acc_stderr\": 0.02841820861940676,\n \"acc_norm\": 0.6764705882352942,\n \"acc_norm_stderr\": 0.02841820861940676\n },\n \"harness|hendrycksTest-professional_psychology|5\": {\n \"acc\": 0.6437908496732027,\n \"acc_stderr\": 0.019373332420724504,\n \"acc_norm\": 0.6437908496732027,\n \"acc_norm_stderr\": 0.019373332420724504\n },\n \"harness|hendrycksTest-public_relations|5\": {\n \"acc\": 0.7090909090909091,\n \"acc_stderr\": 0.04350271442923243,\n \"acc_norm\": 0.7090909090909091,\n \"acc_norm_stderr\": 0.04350271442923243\n },\n \"harness|hendrycksTest-security_studies|5\": {\n \"acc\": 0.6979591836734694,\n \"acc_stderr\": 0.029393609319879804,\n \"acc_norm\": 0.6979591836734694,\n \"acc_norm_stderr\": 0.029393609319879804\n },\n \"harness|hendrycksTest-sociology|5\": {\n \"acc\": 0.8059701492537313,\n \"acc_stderr\": 0.0279626776047689,\n \"acc_norm\": 0.8059701492537313,\n \"acc_norm_stderr\": 0.0279626776047689\n },\n \"harness|hendrycksTest-us_foreign_policy|5\": {\n \"acc\": 0.83,\n \"acc_stderr\": 0.0377525168068637,\n \"acc_norm\": 0.83,\n \"acc_norm_stderr\": 0.0377525168068637\n },\n \"harness|hendrycksTest-virology|5\": {\n \"acc\": 0.5240963855421686,\n \"acc_stderr\": 0.03887971849597264,\n \"acc_norm\": 0.5240963855421686,\n \"acc_norm_stderr\": 0.03887971849597264\n },\n \"harness|hendrycksTest-world_religions|5\": {\n \"acc\": 0.8596491228070176,\n \"acc_stderr\": 0.0266405825391332,\n \"acc_norm\": 0.8596491228070176,\n \"acc_norm_stderr\": 0.0266405825391332\n },\n \"harness|truthfulqa:mc|0\": {\n \"mc1\": 0.36474908200734396,\n \"mc1_stderr\": 0.01685096106172012,\n \"mc2\": 0.5434993224846835,\n \"mc2_stderr\": 0.01537768281733017\n },\n \"harness|winogrande|5\": {\n \"acc\": 0.7955801104972375,\n \"acc_stderr\": 0.011334090612597207\n },\n \"harness|gsm8k|5\": {\n \"acc\": 0.3457164518574678,\n \"acc_stderr\": 0.013100422990441573\n }\n}\n```", "repo_url": "https://huggingface.co/argilla/notus-7b-v1", "leaderboard_url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard", "point_of_contact": "[email protected]", "configs": [{"config_name": "harness_arc_challenge_25", "data_files": [{"split": "2023_11_29T22_16_51.521321", "path": ["**/details_harness|arc:challenge|25_2023-11-29T22-16-51.521321.parquet"]}, {"split": "2023_12_04T17_15_53.519887", "path": ["**/details_harness|arc:challenge|25_2023-12-04T17-15-53.519887.parquet"]}, {"split": "latest", "path": ["**/details_harness|arc:challenge|25_2023-12-04T17-15-53.519887.parquet"]}]}, {"config_name": "harness_drop_3", "data_files": [{"split": "2023_11_29T22_16_51.521321", "path": ["**/details_harness|drop|3_2023-11-29T22-16-51.521321.parquet"]}, {"split": "latest", "path": ["**/details_harness|drop|3_2023-11-29T22-16-51.521321.parquet"]}]}, {"config_name": "harness_gsm8k_5", "data_files": [{"split": "2023_11_29T22_16_51.521321", "path": ["**/details_harness|gsm8k|5_2023-11-29T22-16-51.521321.parquet"]}, {"split": "2023_12_04T17_15_53.519887", "path": ["**/details_harness|gsm8k|5_2023-12-04T17-15-53.519887.parquet"]}, {"split": "latest", "path": ["**/details_harness|gsm8k|5_2023-12-04T17-15-53.519887.parquet"]}]}, {"config_name": "harness_hellaswag_10", "data_files": [{"split": "2023_11_29T22_16_51.521321", "path": ["**/details_harness|hellaswag|10_2023-11-29T22-16-51.521321.parquet"]}, {"split": "2023_12_04T17_15_53.519887", "path": ["**/details_harness|hellaswag|10_2023-12-04T17-15-53.519887.parquet"]}, {"split": "latest", "path": ["**/details_harness|hellaswag|10_2023-12-04T17-15-53.519887.parquet"]}]}, {"config_name": "harness_hendrycksTest_5", "data_files": [{"split": "2023_11_29T22_16_51.521321", "path": ["**/details_harness|hendrycksTest-abstract_algebra|5_2023-11-29T22-16-51.521321.parquet", "**/details_harness|hendrycksTest-anatomy|5_2023-11-29T22-16-51.521321.parquet", "**/details_harness|hendrycksTest-astronomy|5_2023-11-29T22-16-51.521321.parquet", "**/details_harness|hendrycksTest-business_ethics|5_2023-11-29T22-16-51.521321.parquet", "**/details_harness|hendrycksTest-clinical_knowledge|5_2023-11-29T22-16-51.521321.parquet", "**/details_harness|hendrycksTest-college_biology|5_2023-11-29T22-16-51.521321.parquet", "**/details_harness|hendrycksTest-college_chemistry|5_2023-11-29T22-16-51.521321.parquet", "**/details_harness|hendrycksTest-college_computer_science|5_2023-11-29T22-16-51.521321.parquet", "**/details_harness|hendrycksTest-college_mathematics|5_2023-11-29T22-16-51.521321.parquet", "**/details_harness|hendrycksTest-college_medicine|5_2023-11-29T22-16-51.521321.parquet", "**/details_harness|hendrycksTest-college_physics|5_2023-11-29T22-16-51.521321.parquet", "**/details_harness|hendrycksTest-computer_security|5_2023-11-29T22-16-51.521321.parquet", "**/details_harness|hendrycksTest-conceptual_physics|5_2023-11-29T22-16-51.521321.parquet", "**/details_harness|hendrycksTest-econometrics|5_2023-11-29T22-16-51.521321.parquet", "**/details_harness|hendrycksTest-electrical_engineering|5_2023-11-29T22-16-51.521321.parquet", "**/details_harness|hendrycksTest-elementary_mathematics|5_2023-11-29T22-16-51.521321.parquet", "**/details_harness|hendrycksTest-formal_logic|5_2023-11-29T22-16-51.521321.parquet", "**/details_harness|hendrycksTest-global_facts|5_2023-11-29T22-16-51.521321.parquet", "**/details_harness|hendrycksTest-high_school_biology|5_2023-11-29T22-16-51.521321.parquet", "**/details_harness|hendrycksTest-high_school_chemistry|5_2023-11-29T22-16-51.521321.parquet", "**/details_harness|hendrycksTest-high_school_computer_science|5_2023-11-29T22-16-51.521321.parquet", "**/details_harness|hendrycksTest-high_school_european_history|5_2023-11-29T22-16-51.521321.parquet", "**/details_harness|hendrycksTest-high_school_geography|5_2023-11-29T22-16-51.521321.parquet", "**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-11-29T22-16-51.521321.parquet", "**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-11-29T22-16-51.521321.parquet", "**/details_harness|hendrycksTest-high_school_mathematics|5_2023-11-29T22-16-51.521321.parquet", "**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-11-29T22-16-51.521321.parquet", "**/details_harness|hendrycksTest-high_school_physics|5_2023-11-29T22-16-51.521321.parquet", "**/details_harness|hendrycksTest-high_school_psychology|5_2023-11-29T22-16-51.521321.parquet", "**/details_harness|hendrycksTest-high_school_statistics|5_2023-11-29T22-16-51.521321.parquet", "**/details_harness|hendrycksTest-high_school_us_history|5_2023-11-29T22-16-51.521321.parquet", "**/details_harness|hendrycksTest-high_school_world_history|5_2023-11-29T22-16-51.521321.parquet", "**/details_harness|hendrycksTest-human_aging|5_2023-11-29T22-16-51.521321.parquet", "**/details_harness|hendrycksTest-human_sexuality|5_2023-11-29T22-16-51.521321.parquet", "**/details_harness|hendrycksTest-international_law|5_2023-11-29T22-16-51.521321.parquet", "**/details_harness|hendrycksTest-jurisprudence|5_2023-11-29T22-16-51.521321.parquet", "**/details_harness|hendrycksTest-logical_fallacies|5_2023-11-29T22-16-51.521321.parquet", "**/details_harness|hendrycksTest-machine_learning|5_2023-11-29T22-16-51.521321.parquet", "**/details_harness|hendrycksTest-management|5_2023-11-29T22-16-51.521321.parquet", "**/details_harness|hendrycksTest-marketing|5_2023-11-29T22-16-51.521321.parquet", "**/details_harness|hendrycksTest-medical_genetics|5_2023-11-29T22-16-51.521321.parquet", "**/details_harness|hendrycksTest-miscellaneous|5_2023-11-29T22-16-51.521321.parquet", "**/details_harness|hendrycksTest-moral_disputes|5_2023-11-29T22-16-51.521321.parquet", "**/details_harness|hendrycksTest-moral_scenarios|5_2023-11-29T22-16-51.521321.parquet", "**/details_harness|hendrycksTest-nutrition|5_2023-11-29T22-16-51.521321.parquet", "**/details_harness|hendrycksTest-philosophy|5_2023-11-29T22-16-51.521321.parquet", "**/details_harness|hendrycksTest-prehistory|5_2023-11-29T22-16-51.521321.parquet", "**/details_harness|hendrycksTest-professional_accounting|5_2023-11-29T22-16-51.521321.parquet", "**/details_harness|hendrycksTest-professional_law|5_2023-11-29T22-16-51.521321.parquet", "**/details_harness|hendrycksTest-professional_medicine|5_2023-11-29T22-16-51.521321.parquet", "**/details_harness|hendrycksTest-professional_psychology|5_2023-11-29T22-16-51.521321.parquet", "**/details_harness|hendrycksTest-public_relations|5_2023-11-29T22-16-51.521321.parquet", "**/details_harness|hendrycksTest-security_studies|5_2023-11-29T22-16-51.521321.parquet", "**/details_harness|hendrycksTest-sociology|5_2023-11-29T22-16-51.521321.parquet", "**/details_harness|hendrycksTest-us_foreign_policy|5_2023-11-29T22-16-51.521321.parquet", "**/details_harness|hendrycksTest-virology|5_2023-11-29T22-16-51.521321.parquet", "**/details_harness|hendrycksTest-world_religions|5_2023-11-29T22-16-51.521321.parquet"]}, {"split": "2023_12_04T17_15_53.519887", "path": ["**/details_harness|hendrycksTest-abstract_algebra|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-anatomy|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-astronomy|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-business_ethics|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-clinical_knowledge|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-college_biology|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-college_chemistry|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-college_computer_science|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-college_mathematics|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-college_medicine|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-college_physics|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-computer_security|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-conceptual_physics|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-econometrics|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-electrical_engineering|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-elementary_mathematics|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-formal_logic|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-global_facts|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-high_school_biology|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-high_school_chemistry|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-high_school_computer_science|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-high_school_european_history|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-high_school_geography|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-high_school_mathematics|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-high_school_physics|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-high_school_psychology|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-high_school_statistics|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-high_school_us_history|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-high_school_world_history|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-human_aging|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-human_sexuality|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-international_law|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-jurisprudence|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-logical_fallacies|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-machine_learning|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-management|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-marketing|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-medical_genetics|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-miscellaneous|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-moral_disputes|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-moral_scenarios|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-nutrition|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-philosophy|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-prehistory|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-professional_accounting|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-professional_law|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-professional_medicine|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-professional_psychology|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-public_relations|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-security_studies|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-sociology|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-us_foreign_policy|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-virology|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-world_religions|5_2023-12-04T17-15-53.519887.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-abstract_algebra|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-anatomy|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-astronomy|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-business_ethics|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-clinical_knowledge|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-college_biology|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-college_chemistry|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-college_computer_science|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-college_mathematics|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-college_medicine|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-college_physics|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-computer_security|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-conceptual_physics|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-econometrics|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-electrical_engineering|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-elementary_mathematics|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-formal_logic|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-global_facts|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-high_school_biology|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-high_school_chemistry|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-high_school_computer_science|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-high_school_european_history|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-high_school_geography|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-high_school_mathematics|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-high_school_physics|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-high_school_psychology|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-high_school_statistics|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-high_school_us_history|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-high_school_world_history|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-human_aging|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-human_sexuality|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-international_law|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-jurisprudence|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-logical_fallacies|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-machine_learning|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-management|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-marketing|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-medical_genetics|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-miscellaneous|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-moral_disputes|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-moral_scenarios|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-nutrition|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-philosophy|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-prehistory|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-professional_accounting|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-professional_law|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-professional_medicine|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-professional_psychology|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-public_relations|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-security_studies|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-sociology|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-us_foreign_policy|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-virology|5_2023-12-04T17-15-53.519887.parquet", "**/details_harness|hendrycksTest-world_religions|5_2023-12-04T17-15-53.519887.parquet"]}]}, {"config_name": "harness_hendrycksTest_abstract_algebra_5", "data_files": [{"split": "2023_11_29T22_16_51.521321", "path": ["**/details_harness|hendrycksTest-abstract_algebra|5_2023-11-29T22-16-51.521321.parquet"]}, {"split": "2023_12_04T17_15_53.519887", "path": ["**/details_harness|hendrycksTest-abstract_algebra|5_2023-12-04T17-15-53.519887.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-abstract_algebra|5_2023-12-04T17-15-53.519887.parquet"]}]}, {"config_name": "harness_hendrycksTest_anatomy_5", "data_files": [{"split": "2023_11_29T22_16_51.521321", "path": ["**/details_harness|hendrycksTest-anatomy|5_2023-11-29T22-16-51.521321.parquet"]}, {"split": "2023_12_04T17_15_53.519887", "path": ["**/details_harness|hendrycksTest-anatomy|5_2023-12-04T17-15-53.519887.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-anatomy|5_2023-12-04T17-15-53.519887.parquet"]}]}, {"config_name": "harness_hendrycksTest_astronomy_5", "data_files": [{"split": "2023_11_29T22_16_51.521321", "path": ["**/details_harness|hendrycksTest-astronomy|5_2023-11-29T22-16-51.521321.parquet"]}, {"split": "2023_12_04T17_15_53.519887", "path": ["**/details_harness|hendrycksTest-astronomy|5_2023-12-04T17-15-53.519887.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-astronomy|5_2023-12-04T17-15-53.519887.parquet"]}]}, {"config_name": "harness_hendrycksTest_business_ethics_5", "data_files": [{"split": "2023_11_29T22_16_51.521321", "path": ["**/details_harness|hendrycksTest-business_ethics|5_2023-11-29T22-16-51.521321.parquet"]}, {"split": "2023_12_04T17_15_53.519887", "path": ["**/details_harness|hendrycksTest-business_ethics|5_2023-12-04T17-15-53.519887.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-business_ethics|5_2023-12-04T17-15-53.519887.parquet"]}]}, {"config_name": "harness_hendrycksTest_clinical_knowledge_5", "data_files": [{"split": "2023_11_29T22_16_51.521321", "path": ["**/details_harness|hendrycksTest-clinical_knowledge|5_2023-11-29T22-16-51.521321.parquet"]}, {"split": "2023_12_04T17_15_53.519887", "path": ["**/details_harness|hendrycksTest-clinical_knowledge|5_2023-12-04T17-15-53.519887.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-clinical_knowledge|5_2023-12-04T17-15-53.519887.parquet"]}]}, {"config_name": "harness_hendrycksTest_college_biology_5", "data_files": [{"split": "2023_11_29T22_16_51.521321", "path": ["**/details_harness|hendrycksTest-college_biology|5_2023-11-29T22-16-51.521321.parquet"]}, {"split": "2023_12_04T17_15_53.519887", "path": ["**/details_harness|hendrycksTest-college_biology|5_2023-12-04T17-15-53.519887.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-college_biology|5_2023-12-04T17-15-53.519887.parquet"]}]}, {"config_name": "harness_hendrycksTest_college_chemistry_5", "data_files": [{"split": "2023_11_29T22_16_51.521321", "path": ["**/details_harness|hendrycksTest-college_chemistry|5_2023-11-29T22-16-51.521321.parquet"]}, {"split": "2023_12_04T17_15_53.519887", "path": ["**/details_harness|hendrycksTest-college_chemistry|5_2023-12-04T17-15-53.519887.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-college_chemistry|5_2023-12-04T17-15-53.519887.parquet"]}]}, {"config_name": "harness_hendrycksTest_college_computer_science_5", "data_files": [{"split": "2023_11_29T22_16_51.521321", "path": ["**/details_harness|hendrycksTest-college_computer_science|5_2023-11-29T22-16-51.521321.parquet"]}, {"split": "2023_12_04T17_15_53.519887", "path": ["**/details_harness|hendrycksTest-college_computer_science|5_2023-12-04T17-15-53.519887.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-college_computer_science|5_2023-12-04T17-15-53.519887.parquet"]}]}, {"config_name": "harness_hendrycksTest_college_mathematics_5", "data_files": [{"split": "2023_11_29T22_16_51.521321", "path": ["**/details_harness|hendrycksTest-college_mathematics|5_2023-11-29T22-16-51.521321.parquet"]}, {"split": "2023_12_04T17_15_53.519887", "path": ["**/details_harness|hendrycksTest-college_mathematics|5_2023-12-04T17-15-53.519887.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-college_mathematics|5_2023-12-04T17-15-53.519887.parquet"]}]}, {"config_name": "harness_hendrycksTest_college_medicine_5", "data_files": [{"split": "2023_11_29T22_16_51.521321", "path": ["**/details_harness|hendrycksTest-college_medicine|5_2023-11-29T22-16-51.521321.parquet"]}, {"split": "2023_12_04T17_15_53.519887", "path": ["**/details_harness|hendrycksTest-college_medicine|5_2023-12-04T17-15-53.519887.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-college_medicine|5_2023-12-04T17-15-53.519887.parquet"]}]}, {"config_name": "harness_hendrycksTest_college_physics_5", "data_files": [{"split": "2023_11_29T22_16_51.521321", "path": ["**/details_harness|hendrycksTest-college_physics|5_2023-11-29T22-16-51.521321.parquet"]}, {"split": "2023_12_04T17_15_53.519887", "path": ["**/details_harness|hendrycksTest-college_physics|5_2023-12-04T17-15-53.519887.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-college_physics|5_2023-12-04T17-15-53.519887.parquet"]}]}, {"config_name": "harness_hendrycksTest_computer_security_5", "data_files": [{"split": "2023_11_29T22_16_51.521321", "path": ["**/details_harness|hendrycksTest-computer_security|5_2023-11-29T22-16-51.521321.parquet"]}, {"split": "2023_12_04T17_15_53.519887", "path": ["**/details_harness|hendrycksTest-computer_security|5_2023-12-04T17-15-53.519887.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-computer_security|5_2023-12-04T17-15-53.519887.parquet"]}]}, {"config_name": "harness_hendrycksTest_conceptual_physics_5", "data_files": [{"split": "2023_11_29T22_16_51.521321", "path": ["**/details_harness|hendrycksTest-conceptual_physics|5_2023-11-29T22-16-51.521321.parquet"]}, {"split": "2023_12_04T17_15_53.519887", "path": ["**/details_harness|hendrycksTest-conceptual_physics|5_2023-12-04T17-15-53.519887.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-conceptual_physics|5_2023-12-04T17-15-53.519887.parquet"]}]}, {"config_name": "harness_hendrycksTest_econometrics_5", "data_files": [{"split": "2023_11_29T22_16_51.521321", "path": ["**/details_harness|hendrycksTest-econometrics|5_2023-11-29T22-16-51.521321.parquet"]}, {"split": "2023_12_04T17_15_53.519887", "path": ["**/details_harness|hendrycksTest-econometrics|5_2023-12-04T17-15-53.519887.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-econometrics|5_2023-12-04T17-15-53.519887.parquet"]}]}, {"config_name": "harness_hendrycksTest_electrical_engineering_5", "data_files": [{"split": "2023_11_29T22_16_51.521321", "path": ["**/details_harness|hendrycksTest-electrical_engineering|5_2023-11-29T22-16-51.521321.parquet"]}, {"split": "2023_12_04T17_15_53.519887", "path": ["**/details_harness|hendrycksTest-electrical_engineering|5_2023-12-04T17-15-53.519887.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-electrical_engineering|5_2023-12-04T17-15-53.519887.parquet"]}]}, {"config_name": "harness_hendrycksTest_elementary_mathematics_5", "data_files": [{"split": "2023_11_29T22_16_51.521321", "path": ["**/details_harness|hendrycksTest-elementary_mathematics|5_2023-11-29T22-16-51.521321.parquet"]}, {"split": "2023_12_04T17_15_53.519887", "path": ["**/details_harness|hendrycksTest-elementary_mathematics|5_2023-12-04T17-15-53.519887.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-elementary_mathematics|5_2023-12-04T17-15-53.519887.parquet"]}]}, {"config_name": "harness_hendrycksTest_formal_logic_5", "data_files": [{"split": "2023_11_29T22_16_51.521321", "path": ["**/details_harness|hendrycksTest-formal_logic|5_2023-11-29T22-16-51.521321.parquet"]}, {"split": "2023_12_04T17_15_53.519887", "path": ["**/details_harness|hendrycksTest-formal_logic|5_2023-12-04T17-15-53.519887.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-formal_logic|5_2023-12-04T17-15-53.519887.parquet"]}]}, {"config_name": "harness_hendrycksTest_global_facts_5", "data_files": [{"split": "2023_11_29T22_16_51.521321", "path": ["**/details_harness|hendrycksTest-global_facts|5_2023-11-29T22-16-51.521321.parquet"]}, {"split": "2023_12_04T17_15_53.519887", "path": ["**/details_harness|hendrycksTest-global_facts|5_2023-12-04T17-15-53.519887.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-global_facts|5_2023-12-04T17-15-53.519887.parquet"]}]}, {"config_name": "harness_hendrycksTest_high_school_biology_5", "data_files": [{"split": "2023_11_29T22_16_51.521321", "path": ["**/details_harness|hendrycksTest-high_school_biology|5_2023-11-29T22-16-51.521321.parquet"]}, {"split": "2023_12_04T17_15_53.519887", "path": ["**/details_harness|hendrycksTest-high_school_biology|5_2023-12-04T17-15-53.519887.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-high_school_biology|5_2023-12-04T17-15-53.519887.parquet"]}]}, {"config_name": "harness_hendrycksTest_high_school_chemistry_5", "data_files": [{"split": "2023_11_29T22_16_51.521321", "path": ["**/details_harness|hendrycksTest-high_school_chemistry|5_2023-11-29T22-16-51.521321.parquet"]}, {"split": "2023_12_04T17_15_53.519887", "path": ["**/details_harness|hendrycksTest-high_school_chemistry|5_2023-12-04T17-15-53.519887.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-high_school_chemistry|5_2023-12-04T17-15-53.519887.parquet"]}]}, {"config_name": "harness_hendrycksTest_high_school_computer_science_5", "data_files": [{"split": "2023_11_29T22_16_51.521321", "path": ["**/details_harness|hendrycksTest-high_school_computer_science|5_2023-11-29T22-16-51.521321.parquet"]}, {"split": "2023_12_04T17_15_53.519887", "path": ["**/details_harness|hendrycksTest-high_school_computer_science|5_2023-12-04T17-15-53.519887.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-high_school_computer_science|5_2023-12-04T17-15-53.519887.parquet"]}]}, {"config_name": "harness_hendrycksTest_high_school_european_history_5", "data_files": [{"split": "2023_11_29T22_16_51.521321", "path": ["**/details_harness|hendrycksTest-high_school_european_history|5_2023-11-29T22-16-51.521321.parquet"]}, {"split": "2023_12_04T17_15_53.519887", "path": ["**/details_harness|hendrycksTest-high_school_european_history|5_2023-12-04T17-15-53.519887.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-high_school_european_history|5_2023-12-04T17-15-53.519887.parquet"]}]}, {"config_name": "harness_hendrycksTest_high_school_geography_5", "data_files": [{"split": "2023_11_29T22_16_51.521321", "path": ["**/details_harness|hendrycksTest-high_school_geography|5_2023-11-29T22-16-51.521321.parquet"]}, {"split": "2023_12_04T17_15_53.519887", "path": ["**/details_harness|hendrycksTest-high_school_geography|5_2023-12-04T17-15-53.519887.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-high_school_geography|5_2023-12-04T17-15-53.519887.parquet"]}]}, {"config_name": "harness_hendrycksTest_high_school_government_and_politics_5", "data_files": [{"split": "2023_11_29T22_16_51.521321", "path": ["**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-11-29T22-16-51.521321.parquet"]}, {"split": "2023_12_04T17_15_53.519887", "path": ["**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-12-04T17-15-53.519887.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-12-04T17-15-53.519887.parquet"]}]}, {"config_name": "harness_hendrycksTest_high_school_macroeconomics_5", "data_files": [{"split": "2023_11_29T22_16_51.521321", "path": ["**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-11-29T22-16-51.521321.parquet"]}, {"split": "2023_12_04T17_15_53.519887", "path": ["**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-12-04T17-15-53.519887.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-12-04T17-15-53.519887.parquet"]}]}, {"config_name": "harness_hendrycksTest_high_school_mathematics_5", "data_files": [{"split": "2023_11_29T22_16_51.521321", "path": ["**/details_harness|hendrycksTest-high_school_mathematics|5_2023-11-29T22-16-51.521321.parquet"]}, {"split": "2023_12_04T17_15_53.519887", "path": ["**/details_harness|hendrycksTest-high_school_mathematics|5_2023-12-04T17-15-53.519887.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-high_school_mathematics|5_2023-12-04T17-15-53.519887.parquet"]}]}, {"config_name": "harness_hendrycksTest_high_school_microeconomics_5", "data_files": [{"split": "2023_11_29T22_16_51.521321", "path": ["**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-11-29T22-16-51.521321.parquet"]}, {"split": "2023_12_04T17_15_53.519887", "path": ["**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-12-04T17-15-53.519887.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-12-04T17-15-53.519887.parquet"]}]}, {"config_name": "harness_hendrycksTest_high_school_physics_5", "data_files": [{"split": "2023_11_29T22_16_51.521321", "path": ["**/details_harness|hendrycksTest-high_school_physics|5_2023-11-29T22-16-51.521321.parquet"]}, {"split": "2023_12_04T17_15_53.519887", "path": ["**/details_harness|hendrycksTest-high_school_physics|5_2023-12-04T17-15-53.519887.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-high_school_physics|5_2023-12-04T17-15-53.519887.parquet"]}]}, {"config_name": "harness_hendrycksTest_high_school_psychology_5", "data_files": [{"split": "2023_11_29T22_16_51.521321", "path": ["**/details_harness|hendrycksTest-high_school_psychology|5_2023-11-29T22-16-51.521321.parquet"]}, {"split": "2023_12_04T17_15_53.519887", "path": ["**/details_harness|hendrycksTest-high_school_psychology|5_2023-12-04T17-15-53.519887.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-high_school_psychology|5_2023-12-04T17-15-53.519887.parquet"]}]}, {"config_name": "harness_hendrycksTest_high_school_statistics_5", "data_files": [{"split": "2023_11_29T22_16_51.521321", "path": ["**/details_harness|hendrycksTest-high_school_statistics|5_2023-11-29T22-16-51.521321.parquet"]}, {"split": "2023_12_04T17_15_53.519887", "path": ["**/details_harness|hendrycksTest-high_school_statistics|5_2023-12-04T17-15-53.519887.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-high_school_statistics|5_2023-12-04T17-15-53.519887.parquet"]}]}, {"config_name": "harness_hendrycksTest_high_school_us_history_5", "data_files": [{"split": "2023_11_29T22_16_51.521321", "path": ["**/details_harness|hendrycksTest-high_school_us_history|5_2023-11-29T22-16-51.521321.parquet"]}, {"split": "2023_12_04T17_15_53.519887", "path": ["**/details_harness|hendrycksTest-high_school_us_history|5_2023-12-04T17-15-53.519887.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-high_school_us_history|5_2023-12-04T17-15-53.519887.parquet"]}]}, {"config_name": "harness_hendrycksTest_high_school_world_history_5", "data_files": [{"split": "2023_11_29T22_16_51.521321", "path": ["**/details_harness|hendrycksTest-high_school_world_history|5_2023-11-29T22-16-51.521321.parquet"]}, {"split": "2023_12_04T17_15_53.519887", "path": ["**/details_harness|hendrycksTest-high_school_world_history|5_2023-12-04T17-15-53.519887.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-high_school_world_history|5_2023-12-04T17-15-53.519887.parquet"]}]}, {"config_name": "harness_hendrycksTest_human_aging_5", "data_files": [{"split": "2023_11_29T22_16_51.521321", "path": ["**/details_harness|hendrycksTest-human_aging|5_2023-11-29T22-16-51.521321.parquet"]}, {"split": "2023_12_04T17_15_53.519887", "path": ["**/details_harness|hendrycksTest-human_aging|5_2023-12-04T17-15-53.519887.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-human_aging|5_2023-12-04T17-15-53.519887.parquet"]}]}, {"config_name": "harness_hendrycksTest_human_sexuality_5", "data_files": [{"split": "2023_11_29T22_16_51.521321", "path": ["**/details_harness|hendrycksTest-human_sexuality|5_2023-11-29T22-16-51.521321.parquet"]}, {"split": "2023_12_04T17_15_53.519887", "path": ["**/details_harness|hendrycksTest-human_sexuality|5_2023-12-04T17-15-53.519887.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-human_sexuality|5_2023-12-04T17-15-53.519887.parquet"]}]}, {"config_name": "harness_hendrycksTest_international_law_5", "data_files": [{"split": "2023_11_29T22_16_51.521321", "path": ["**/details_harness|hendrycksTest-international_law|5_2023-11-29T22-16-51.521321.parquet"]}, {"split": "2023_12_04T17_15_53.519887", "path": ["**/details_harness|hendrycksTest-international_law|5_2023-12-04T17-15-53.519887.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-international_law|5_2023-12-04T17-15-53.519887.parquet"]}]}, {"config_name": "harness_hendrycksTest_jurisprudence_5", "data_files": [{"split": "2023_11_29T22_16_51.521321", "path": ["**/details_harness|hendrycksTest-jurisprudence|5_2023-11-29T22-16-51.521321.parquet"]}, {"split": "2023_12_04T17_15_53.519887", "path": ["**/details_harness|hendrycksTest-jurisprudence|5_2023-12-04T17-15-53.519887.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-jurisprudence|5_2023-12-04T17-15-53.519887.parquet"]}]}, {"config_name": "harness_hendrycksTest_logical_fallacies_5", "data_files": [{"split": "2023_11_29T22_16_51.521321", "path": ["**/details_harness|hendrycksTest-logical_fallacies|5_2023-11-29T22-16-51.521321.parquet"]}, {"split": "2023_12_04T17_15_53.519887", "path": ["**/details_harness|hendrycksTest-logical_fallacies|5_2023-12-04T17-15-53.519887.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-logical_fallacies|5_2023-12-04T17-15-53.519887.parquet"]}]}, {"config_name": "harness_hendrycksTest_machine_learning_5", "data_files": [{"split": "2023_11_29T22_16_51.521321", "path": ["**/details_harness|hendrycksTest-machine_learning|5_2023-11-29T22-16-51.521321.parquet"]}, {"split": "2023_12_04T17_15_53.519887", "path": ["**/details_harness|hendrycksTest-machine_learning|5_2023-12-04T17-15-53.519887.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-machine_learning|5_2023-12-04T17-15-53.519887.parquet"]}]}, {"config_name": "harness_hendrycksTest_management_5", "data_files": [{"split": "2023_11_29T22_16_51.521321", "path": ["**/details_harness|hendrycksTest-management|5_2023-11-29T22-16-51.521321.parquet"]}, {"split": "2023_12_04T17_15_53.519887", "path": ["**/details_harness|hendrycksTest-management|5_2023-12-04T17-15-53.519887.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-management|5_2023-12-04T17-15-53.519887.parquet"]}]}, {"config_name": "harness_hendrycksTest_marketing_5", "data_files": [{"split": "2023_11_29T22_16_51.521321", "path": ["**/details_harness|hendrycksTest-marketing|5_2023-11-29T22-16-51.521321.parquet"]}, {"split": "2023_12_04T17_15_53.519887", "path": ["**/details_harness|hendrycksTest-marketing|5_2023-12-04T17-15-53.519887.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-marketing|5_2023-12-04T17-15-53.519887.parquet"]}]}, {"config_name": "harness_hendrycksTest_medical_genetics_5", "data_files": [{"split": "2023_11_29T22_16_51.521321", "path": ["**/details_harness|hendrycksTest-medical_genetics|5_2023-11-29T22-16-51.521321.parquet"]}, {"split": "2023_12_04T17_15_53.519887", "path": ["**/details_harness|hendrycksTest-medical_genetics|5_2023-12-04T17-15-53.519887.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-medical_genetics|5_2023-12-04T17-15-53.519887.parquet"]}]}, {"config_name": "harness_hendrycksTest_miscellaneous_5", "data_files": [{"split": "2023_11_29T22_16_51.521321", "path": ["**/details_harness|hendrycksTest-miscellaneous|5_2023-11-29T22-16-51.521321.parquet"]}, {"split": "2023_12_04T17_15_53.519887", "path": ["**/details_harness|hendrycksTest-miscellaneous|5_2023-12-04T17-15-53.519887.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-miscellaneous|5_2023-12-04T17-15-53.519887.parquet"]}]}, {"config_name": "harness_hendrycksTest_moral_disputes_5", "data_files": [{"split": "2023_11_29T22_16_51.521321", "path": ["**/details_harness|hendrycksTest-moral_disputes|5_2023-11-29T22-16-51.521321.parquet"]}, {"split": "2023_12_04T17_15_53.519887", "path": ["**/details_harness|hendrycksTest-moral_disputes|5_2023-12-04T17-15-53.519887.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-moral_disputes|5_2023-12-04T17-15-53.519887.parquet"]}]}, {"config_name": "harness_hendrycksTest_moral_scenarios_5", "data_files": [{"split": "2023_11_29T22_16_51.521321", "path": ["**/details_harness|hendrycksTest-moral_scenarios|5_2023-11-29T22-16-51.521321.parquet"]}, {"split": "2023_12_04T17_15_53.519887", "path": ["**/details_harness|hendrycksTest-moral_scenarios|5_2023-12-04T17-15-53.519887.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-moral_scenarios|5_2023-12-04T17-15-53.519887.parquet"]}]}, {"config_name": "harness_hendrycksTest_nutrition_5", "data_files": [{"split": "2023_11_29T22_16_51.521321", "path": ["**/details_harness|hendrycksTest-nutrition|5_2023-11-29T22-16-51.521321.parquet"]}, {"split": "2023_12_04T17_15_53.519887", "path": ["**/details_harness|hendrycksTest-nutrition|5_2023-12-04T17-15-53.519887.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-nutrition|5_2023-12-04T17-15-53.519887.parquet"]}]}, {"config_name": "harness_hendrycksTest_philosophy_5", "data_files": [{"split": "2023_11_29T22_16_51.521321", "path": ["**/details_harness|hendrycksTest-philosophy|5_2023-11-29T22-16-51.521321.parquet"]}, {"split": "2023_12_04T17_15_53.519887", "path": ["**/details_harness|hendrycksTest-philosophy|5_2023-12-04T17-15-53.519887.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-philosophy|5_2023-12-04T17-15-53.519887.parquet"]}]}, {"config_name": "harness_hendrycksTest_prehistory_5", "data_files": [{"split": "2023_11_29T22_16_51.521321", "path": ["**/details_harness|hendrycksTest-prehistory|5_2023-11-29T22-16-51.521321.parquet"]}, {"split": "2023_12_04T17_15_53.519887", "path": ["**/details_harness|hendrycksTest-prehistory|5_2023-12-04T17-15-53.519887.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-prehistory|5_2023-12-04T17-15-53.519887.parquet"]}]}, {"config_name": "harness_hendrycksTest_professional_accounting_5", "data_files": [{"split": "2023_11_29T22_16_51.521321", "path": ["**/details_harness|hendrycksTest-professional_accounting|5_2023-11-29T22-16-51.521321.parquet"]}, {"split": "2023_12_04T17_15_53.519887", "path": ["**/details_harness|hendrycksTest-professional_accounting|5_2023-12-04T17-15-53.519887.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-professional_accounting|5_2023-12-04T17-15-53.519887.parquet"]}]}, {"config_name": "harness_hendrycksTest_professional_law_5", "data_files": [{"split": "2023_11_29T22_16_51.521321", "path": ["**/details_harness|hendrycksTest-professional_law|5_2023-11-29T22-16-51.521321.parquet"]}, {"split": "2023_12_04T17_15_53.519887", "path": ["**/details_harness|hendrycksTest-professional_law|5_2023-12-04T17-15-53.519887.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-professional_law|5_2023-12-04T17-15-53.519887.parquet"]}]}, {"config_name": "harness_hendrycksTest_professional_medicine_5", "data_files": [{"split": "2023_11_29T22_16_51.521321", "path": ["**/details_harness|hendrycksTest-professional_medicine|5_2023-11-29T22-16-51.521321.parquet"]}, {"split": "2023_12_04T17_15_53.519887", "path": ["**/details_harness|hendrycksTest-professional_medicine|5_2023-12-04T17-15-53.519887.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-professional_medicine|5_2023-12-04T17-15-53.519887.parquet"]}]}, {"config_name": "harness_hendrycksTest_professional_psychology_5", "data_files": [{"split": "2023_11_29T22_16_51.521321", "path": ["**/details_harness|hendrycksTest-professional_psychology|5_2023-11-29T22-16-51.521321.parquet"]}, {"split": "2023_12_04T17_15_53.519887", "path": ["**/details_harness|hendrycksTest-professional_psychology|5_2023-12-04T17-15-53.519887.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-professional_psychology|5_2023-12-04T17-15-53.519887.parquet"]}]}, {"config_name": "harness_hendrycksTest_public_relations_5", "data_files": [{"split": "2023_11_29T22_16_51.521321", "path": ["**/details_harness|hendrycksTest-public_relations|5_2023-11-29T22-16-51.521321.parquet"]}, {"split": "2023_12_04T17_15_53.519887", "path": ["**/details_harness|hendrycksTest-public_relations|5_2023-12-04T17-15-53.519887.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-public_relations|5_2023-12-04T17-15-53.519887.parquet"]}]}, {"config_name": "harness_hendrycksTest_security_studies_5", "data_files": [{"split": "2023_11_29T22_16_51.521321", "path": ["**/details_harness|hendrycksTest-security_studies|5_2023-11-29T22-16-51.521321.parquet"]}, {"split": "2023_12_04T17_15_53.519887", "path": ["**/details_harness|hendrycksTest-security_studies|5_2023-12-04T17-15-53.519887.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-security_studies|5_2023-12-04T17-15-53.519887.parquet"]}]}, {"config_name": "harness_hendrycksTest_sociology_5", "data_files": [{"split": "2023_11_29T22_16_51.521321", "path": ["**/details_harness|hendrycksTest-sociology|5_2023-11-29T22-16-51.521321.parquet"]}, {"split": "2023_12_04T17_15_53.519887", "path": ["**/details_harness|hendrycksTest-sociology|5_2023-12-04T17-15-53.519887.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-sociology|5_2023-12-04T17-15-53.519887.parquet"]}]}, {"config_name": "harness_hendrycksTest_us_foreign_policy_5", "data_files": [{"split": "2023_11_29T22_16_51.521321", "path": ["**/details_harness|hendrycksTest-us_foreign_policy|5_2023-11-29T22-16-51.521321.parquet"]}, {"split": "2023_12_04T17_15_53.519887", "path": ["**/details_harness|hendrycksTest-us_foreign_policy|5_2023-12-04T17-15-53.519887.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-us_foreign_policy|5_2023-12-04T17-15-53.519887.parquet"]}]}, {"config_name": "harness_hendrycksTest_virology_5", "data_files": [{"split": "2023_11_29T22_16_51.521321", "path": ["**/details_harness|hendrycksTest-virology|5_2023-11-29T22-16-51.521321.parquet"]}, {"split": "2023_12_04T17_15_53.519887", "path": ["**/details_harness|hendrycksTest-virology|5_2023-12-04T17-15-53.519887.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-virology|5_2023-12-04T17-15-53.519887.parquet"]}]}, {"config_name": "harness_hendrycksTest_world_religions_5", "data_files": [{"split": "2023_11_29T22_16_51.521321", "path": ["**/details_harness|hendrycksTest-world_religions|5_2023-11-29T22-16-51.521321.parquet"]}, {"split": "2023_12_04T17_15_53.519887", "path": ["**/details_harness|hendrycksTest-world_religions|5_2023-12-04T17-15-53.519887.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-world_religions|5_2023-12-04T17-15-53.519887.parquet"]}]}, {"config_name": "harness_truthfulqa_mc_0", "data_files": [{"split": "2023_11_29T22_16_51.521321", "path": ["**/details_harness|truthfulqa:mc|0_2023-11-29T22-16-51.521321.parquet"]}, {"split": "2023_12_04T17_15_53.519887", "path": ["**/details_harness|truthfulqa:mc|0_2023-12-04T17-15-53.519887.parquet"]}, {"split": "latest", "path": ["**/details_harness|truthfulqa:mc|0_2023-12-04T17-15-53.519887.parquet"]}]}, {"config_name": "harness_winogrande_5", "data_files": [{"split": "2023_11_29T22_16_51.521321", "path": ["**/details_harness|winogrande|5_2023-11-29T22-16-51.521321.parquet"]}, {"split": "2023_12_04T17_15_53.519887", "path": ["**/details_harness|winogrande|5_2023-12-04T17-15-53.519887.parquet"]}, {"split": "latest", "path": ["**/details_harness|winogrande|5_2023-12-04T17-15-53.519887.parquet"]}]}, {"config_name": "results", "data_files": [{"split": "2023_11_29T22_16_51.521321", "path": ["results_2023-11-29T22-16-51.521321.parquet"]}, {"split": "2023_12_04T17_15_53.519887", "path": ["results_2023-12-04T17-15-53.519887.parquet"]}, {"split": "latest", "path": ["results_2023-12-04T17-15-53.519887.parquet"]}]}]} | 2023-12-04T17:19:30+00:00 | [] | [] | TAGS
#region-us
|
# Dataset Card for Evaluation run of argilla/notus-7b-v1
## Dataset Description
- Homepage:
- Repository: URL
- Paper:
- Leaderboard: URL
- Point of Contact: clementine@URL
### Dataset Summary
Dataset automatically created during the evaluation run of model argilla/notus-7b-v1 on the Open LLM Leaderboard.
The dataset is composed of 64 configuration, each one coresponding to one of the evaluated task.
The dataset has been created from 2 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always pointing to the latest results.
An additional configuration "results" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the Open LLM Leaderboard).
To load the details from a run, you can for instance do the following:
## Latest results
These are the latest results from run 2023-12-04T17:15:53.519887(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the "latest" split for each eval):
### Supported Tasks and Leaderboards
### Languages
## Dataset Structure
### Data Instances
### Data Fields
### Data Splits
## Dataset Creation
### Curation Rationale
### Source Data
#### Initial Data Collection and Normalization
#### Who are the source language producers?
### Annotations
#### Annotation process
#### Who are the annotators?
### Personal and Sensitive Information
## Considerations for Using the Data
### Social Impact of Dataset
### Discussion of Biases
### Other Known Limitations
## Additional Information
### Dataset Curators
### Licensing Information
### Contributions
| [
"# Dataset Card for Evaluation run of argilla/notus-7b-v1",
"## Dataset Description\n\n- Homepage: \n- Repository: URL\n- Paper: \n- Leaderboard: URL\n- Point of Contact: clementine@URL",
"### Dataset Summary\n\nDataset automatically created during the evaluation run of model argilla/notus-7b-v1 on the Open LLM Leaderboard.\n\nThe dataset is composed of 64 configuration, each one coresponding to one of the evaluated task.\n\nThe dataset has been created from 2 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The \"train\" split is always pointing to the latest results.\n\nAn additional configuration \"results\" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the Open LLM Leaderboard).\n\nTo load the details from a run, you can for instance do the following:",
"## Latest results\n\nThese are the latest results from run 2023-12-04T17:15:53.519887(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the \"latest\" split for each eval):",
"### Supported Tasks and Leaderboards",
"### Languages",
"## Dataset Structure",
"### Data Instances",
"### Data Fields",
"### Data Splits",
"## Dataset Creation",
"### Curation Rationale",
"### Source Data",
"#### Initial Data Collection and Normalization",
"#### Who are the source language producers?",
"### Annotations",
"#### Annotation process",
"#### Who are the annotators?",
"### Personal and Sensitive Information",
"## Considerations for Using the Data",
"### Social Impact of Dataset",
"### Discussion of Biases",
"### Other Known Limitations",
"## Additional Information",
"### Dataset Curators",
"### Licensing Information",
"### Contributions"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for Evaluation run of argilla/notus-7b-v1",
"## Dataset Description\n\n- Homepage: \n- Repository: URL\n- Paper: \n- Leaderboard: URL\n- Point of Contact: clementine@URL",
"### Dataset Summary\n\nDataset automatically created during the evaluation run of model argilla/notus-7b-v1 on the Open LLM Leaderboard.\n\nThe dataset is composed of 64 configuration, each one coresponding to one of the evaluated task.\n\nThe dataset has been created from 2 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The \"train\" split is always pointing to the latest results.\n\nAn additional configuration \"results\" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the Open LLM Leaderboard).\n\nTo load the details from a run, you can for instance do the following:",
"## Latest results\n\nThese are the latest results from run 2023-12-04T17:15:53.519887(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the \"latest\" split for each eval):",
"### Supported Tasks and Leaderboards",
"### Languages",
"## Dataset Structure",
"### Data Instances",
"### Data Fields",
"### Data Splits",
"## Dataset Creation",
"### Curation Rationale",
"### Source Data",
"#### Initial Data Collection and Normalization",
"#### Who are the source language producers?",
"### Annotations",
"#### Annotation process",
"#### Who are the annotators?",
"### Personal and Sensitive Information",
"## Considerations for Using the Data",
"### Social Impact of Dataset",
"### Discussion of Biases",
"### Other Known Limitations",
"## Additional Information",
"### Dataset Curators",
"### Licensing Information",
"### Contributions"
] | [
6,
19,
31,
168,
67,
10,
4,
6,
6,
5,
5,
5,
7,
4,
10,
10,
5,
5,
9,
8,
8,
7,
8,
7,
5,
6,
6,
5
] | [
"passage: TAGS\n#region-us \n# Dataset Card for Evaluation run of argilla/notus-7b-v1## Dataset Description\n\n- Homepage: \n- Repository: URL\n- Paper: \n- Leaderboard: URL\n- Point of Contact: clementine@URL### Dataset Summary\n\nDataset automatically created during the evaluation run of model argilla/notus-7b-v1 on the Open LLM Leaderboard.\n\nThe dataset is composed of 64 configuration, each one coresponding to one of the evaluated task.\n\nThe dataset has been created from 2 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The \"train\" split is always pointing to the latest results.\n\nAn additional configuration \"results\" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the Open LLM Leaderboard).\n\nTo load the details from a run, you can for instance do the following:## Latest results\n\nThese are the latest results from run 2023-12-04T17:15:53.519887(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the \"latest\" split for each eval):### Supported Tasks and Leaderboards### Languages## Dataset Structure### Data Instances### Data Fields### Data Splits## Dataset Creation### Curation Rationale### Source Data#### Initial Data Collection and Normalization#### Who are the source language producers?### Annotations#### Annotation process#### Who are the annotators?### Personal and Sensitive Information## Considerations for Using the Data### Social Impact of Dataset### Discussion of Biases### Other Known Limitations## Additional Information### Dataset Curators### Licensing Information### Contributions"
] |
b9add417edf778df41965ff84b979a2d77883649 |
# Become a living god forums dataset
This is a dataset of posts scraped from the top 100 new pages of the spirituality forum https://forum.becomealivinggod.com/
- **Developed by:** Takeraparterer
- **License:** Creative Commons Attribution-NonCommercial-ShareAlike 3.0
Please contact me via community tab if you wish for this to be taken down.
## Format:
```
{"Post_Id - Title":[["username","message"], ...] ...}
``` | takeraparterer/Become-A-Living-God-Forum | [
"license:cc-by-nc-sa-3.0",
"region:us"
] | 2023-11-29T23:01:02+00:00 | {"license": "cc-by-nc-sa-3.0"} | 2023-11-30T06:11:06+00:00 | [] | [] | TAGS
#license-cc-by-nc-sa-3.0 #region-us
|
# Become a living god forums dataset
This is a dataset of posts scraped from the top 100 new pages of the spirituality forum URL
- Developed by: Takeraparterer
- License: Creative Commons Attribution-NonCommercial-ShareAlike 3.0
Please contact me via community tab if you wish for this to be taken down.
## Format:
| [
"# Become a living god forums dataset\n\nThis is a dataset of posts scraped from the top 100 new pages of the spirituality forum URL\n\n- Developed by: Takeraparterer\n- License: Creative Commons Attribution-NonCommercial-ShareAlike 3.0\n\nPlease contact me via community tab if you wish for this to be taken down.",
"## Format:"
] | [
"TAGS\n#license-cc-by-nc-sa-3.0 #region-us \n",
"# Become a living god forums dataset\n\nThis is a dataset of posts scraped from the top 100 new pages of the spirituality forum URL\n\n- Developed by: Takeraparterer\n- License: Creative Commons Attribution-NonCommercial-ShareAlike 3.0\n\nPlease contact me via community tab if you wish for this to be taken down.",
"## Format:"
] | [
19,
70,
3
] | [
"passage: TAGS\n#license-cc-by-nc-sa-3.0 #region-us \n# Become a living god forums dataset\n\nThis is a dataset of posts scraped from the top 100 new pages of the spirituality forum URL\n\n- Developed by: Takeraparterer\n- License: Creative Commons Attribution-NonCommercial-ShareAlike 3.0\n\nPlease contact me via community tab if you wish for this to be taken down.## Format:"
] |
f6bcd1850a758d10f5a8efc004e9900630a48cb8 | # Dataset Card for "handling_charges_v1"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | paul-w-qs/handling_charges_v1 | [
"region:us"
] | 2023-11-29T23:08:21+00:00 | {"configs": [{"config_name": "default", "data_files": [{"split": "train", "path": "data/train-*"}]}], "dataset_info": {"features": [{"name": "image", "dtype": "image"}, {"name": "JSON_LABEL", "dtype": "string"}], "splits": [{"name": "train", "num_bytes": 84923820.0, "num_examples": 514}], "download_size": 84024431, "dataset_size": 84923820.0}} | 2023-11-29T23:08:52+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "handling_charges_v1"
More Information needed | [
"# Dataset Card for \"handling_charges_v1\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"handling_charges_v1\"\n\nMore Information needed"
] | [
6,
17
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"handling_charges_v1\"\n\nMore Information needed"
] |
c8cdd671d84ba59f81259cc03f9f6dd821aa1e24 | # Dataset Card for "tokenized_t5_small_context_len_256"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | yardeny/tokenized_t5_small_context_len_256 | [
"region:us"
] | 2023-11-29T23:28:14+00:00 | {"dataset_info": {"features": [{"name": "input_ids", "sequence": "int32"}, {"name": "attention_mask", "sequence": "int8"}], "splits": [{"name": "train", "num_bytes": 14651743334, "num_examples": 80462898}], "download_size": 5410854109, "dataset_size": 14651743334}} | 2023-11-29T23:40:31+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "tokenized_t5_small_context_len_256"
More Information needed | [
"# Dataset Card for \"tokenized_t5_small_context_len_256\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"tokenized_t5_small_context_len_256\"\n\nMore Information needed"
] | [
6,
26
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"tokenized_t5_small_context_len_256\"\n\nMore Information needed"
] |
6b0868446b1a78c444969be8340f3c253e9bb7e1 | # Dataset Card for "safety-TRAIN"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | sam1120/safety-utcustom-TRAIN | [
"region:us"
] | 2023-11-29T23:38:30+00:00 | {"dataset_info": {"features": [{"name": "name", "dtype": "string"}, {"name": "pixel_values", "dtype": "image"}, {"name": "labels", "dtype": "image"}], "splits": [{"name": "train", "num_bytes": 2904492356.0, "num_examples": 224}], "download_size": 719471263, "dataset_size": 2904492356.0}} | 2023-11-29T23:42:16+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "safety-TRAIN"
More Information needed | [
"# Dataset Card for \"safety-TRAIN\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"safety-TRAIN\"\n\nMore Information needed"
] | [
6,
15
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"safety-TRAIN\"\n\nMore Information needed"
] |
f78f0af4abdddec71daba77977d00eaabd5567dd | # Dataset Card for "terrain-jackal-full-391"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | sam1120/safety-utcustom-terrain-jackal-full-391 | [
"region:us"
] | 2023-11-29T23:42:15+00:00 | {"dataset_info": {"features": [{"name": "name", "dtype": "string"}, {"name": "pixel_values", "dtype": "image"}, {"name": "labels", "dtype": "image"}], "splits": [{"name": "train", "num_bytes": 1086671777.0, "num_examples": 391}], "download_size": 315061316, "dataset_size": 1086671777.0}} | 2023-11-29T23:51:30+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "terrain-jackal-full-391"
More Information needed | [
"# Dataset Card for \"terrain-jackal-full-391\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"terrain-jackal-full-391\"\n\nMore Information needed"
] | [
6,
19
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"terrain-jackal-full-391\"\n\nMore Information needed"
] |
21776cf428d25cdb7f33e0aa5fb51e523fa1258b | # Dataset Card for "processed_t5_small_context_len_256"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | yardeny/processed_t5_small_context_len_256 | [
"region:us"
] | 2023-11-29T23:46:05+00:00 | {"dataset_info": {"features": [{"name": "input_ids", "sequence": "int32"}, {"name": "attention_mask", "sequence": "int8"}], "splits": [{"name": "train", "num_bytes": 14043993936.0, "num_examples": 10903722}], "download_size": 5229292424, "dataset_size": 14043993936.0}} | 2023-11-30T00:14:36+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "processed_t5_small_context_len_256"
More Information needed | [
"# Dataset Card for \"processed_t5_small_context_len_256\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"processed_t5_small_context_len_256\"\n\nMore Information needed"
] | [
6,
25
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"processed_t5_small_context_len_256\"\n\nMore Information needed"
] |
3263cf7e41c5a6e6c4f7731e34d710371710172e | # Dataset Card for "translation_guc_spa"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | Broomva/translation_guc_spa | [
"region:us"
] | 2023-11-30T00:20:00+00:00 | {"configs": [{"config_name": "default", "data_files": [{"split": "train", "path": "data/train-*"}, {"split": "validation", "path": "data/validation-*"}, {"split": "test", "path": "data/test-*"}]}], "dataset_info": {"features": [{"name": "id", "dtype": "int64"}, {"name": "translation", "struct": [{"name": "guc", "dtype": "string"}, {"name": "spa", "dtype": "string"}]}], "splits": [{"name": "train", "num_bytes": 13179247, "num_examples": 76676}, {"name": "validation", "num_bytes": 3254055, "num_examples": 19170}, {"name": "test", "num_bytes": 4127645, "num_examples": 23962}], "download_size": 13149156, "dataset_size": 20560947}} | 2023-12-01T06:13:45+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "translation_guc_spa"
More Information needed | [
"# Dataset Card for \"translation_guc_spa\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"translation_guc_spa\"\n\nMore Information needed"
] | [
6,
17
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"translation_guc_spa\"\n\nMore Information needed"
] |
fc25d84142ae545909fdd16304fc3c53bfa3aaff | Cleaned and/or fixed dataset of PIPPA (https://huggingface.co/datasets/PygmalionAI/PIPPA), without the formatting and random char issues.
Can be used as calibration dataset for exllamav2, like for goliath-rpcal (https://huggingface.co/Panchovix/goliath-120b-exl2-rpcal)
All credits to the Pygmalion team and Undi. | royallab/PIPPA-cleaned | [
"license:apache-2.0",
"not-for-all-audiences",
"conversational",
"roleplay",
"custom-format",
"a.",
"region:us"
] | 2023-11-30T00:26:20+00:00 | {"license": "apache-2.0", "pretty_name": "PIPPA - Personal Interaction Pairs Between People and AI", "tags": ["not-for-all-audiences", "conversational", "roleplay", "custom-format", "a."], "viewer": false} | 2023-11-30T00:26:51+00:00 | [] | [] | TAGS
#license-apache-2.0 #not-for-all-audiences #conversational #roleplay #custom-format #a. #region-us
| Cleaned and/or fixed dataset of PIPPA (URL without the formatting and random char issues.
Can be used as calibration dataset for exllamav2, like for goliath-rpcal (URL
All credits to the Pygmalion team and Undi. | [] | [
"TAGS\n#license-apache-2.0 #not-for-all-audiences #conversational #roleplay #custom-format #a. #region-us \n"
] | [
39
] | [
"passage: TAGS\n#license-apache-2.0 #not-for-all-audiences #conversational #roleplay #custom-format #a. #region-us \n"
] |
51774f14bbbd339badca95da3a1854572b092c8e | # Dataset Card for "github-issues"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | pigpeter/github-issues | [
"region:us"
] | 2023-11-30T01:30:07+00:00 | {"dataset_info": {"features": [{"name": "url", "dtype": "string"}, {"name": "repository_url", "dtype": "string"}, {"name": "labels_url", "dtype": "string"}, {"name": "comments_url", "dtype": "string"}, {"name": "events_url", "dtype": "string"}, {"name": "html_url", "dtype": "string"}, {"name": "id", "dtype": "int64"}, {"name": "node_id", "dtype": "string"}, {"name": "number", "dtype": "int64"}, {"name": "title", "dtype": "string"}, {"name": "user", "struct": [{"name": "login", "dtype": "string"}, {"name": "id", "dtype": "int64"}, {"name": "node_id", "dtype": "string"}, {"name": "avatar_url", "dtype": "string"}, {"name": "gravatar_id", "dtype": "string"}, {"name": "url", "dtype": "string"}, {"name": "html_url", "dtype": "string"}, {"name": "followers_url", "dtype": "string"}, {"name": "following_url", "dtype": "string"}, {"name": "gists_url", "dtype": "string"}, {"name": "starred_url", "dtype": "string"}, {"name": "subscriptions_url", "dtype": "string"}, {"name": "organizations_url", "dtype": "string"}, {"name": "repos_url", "dtype": "string"}, {"name": "events_url", "dtype": "string"}, {"name": "received_events_url", "dtype": "string"}, {"name": "type", "dtype": "string"}, {"name": "site_admin", "dtype": "bool"}]}, {"name": "labels", "list": [{"name": "id", "dtype": "int64"}, {"name": "node_id", "dtype": "string"}, {"name": "url", "dtype": "string"}, {"name": "name", "dtype": "string"}, {"name": "color", "dtype": "string"}, {"name": "default", "dtype": "bool"}, {"name": "description", "dtype": "string"}]}, {"name": "state", "dtype": "string"}, {"name": "locked", "dtype": "bool"}, {"name": "assignee", "struct": [{"name": "login", "dtype": "string"}, {"name": "id", "dtype": "int64"}, {"name": "node_id", "dtype": "string"}, {"name": "avatar_url", "dtype": "string"}, {"name": "gravatar_id", "dtype": "string"}, {"name": "url", "dtype": "string"}, {"name": "html_url", "dtype": "string"}, {"name": "followers_url", "dtype": "string"}, {"name": "following_url", "dtype": "string"}, {"name": "gists_url", "dtype": "string"}, {"name": "starred_url", "dtype": "string"}, {"name": "subscriptions_url", "dtype": "string"}, {"name": "organizations_url", "dtype": "string"}, {"name": "repos_url", "dtype": "string"}, {"name": "events_url", "dtype": "string"}, {"name": "received_events_url", "dtype": "string"}, {"name": "type", "dtype": "string"}, {"name": "site_admin", "dtype": "bool"}]}, {"name": "assignees", "list": [{"name": "login", "dtype": "string"}, {"name": "id", "dtype": "int64"}, {"name": "node_id", "dtype": "string"}, {"name": "avatar_url", "dtype": "string"}, {"name": "gravatar_id", "dtype": "string"}, {"name": "url", "dtype": "string"}, {"name": "html_url", "dtype": "string"}, {"name": "followers_url", "dtype": "string"}, {"name": "following_url", "dtype": "string"}, {"name": "gists_url", "dtype": "string"}, {"name": "starred_url", "dtype": "string"}, {"name": "subscriptions_url", "dtype": "string"}, {"name": "organizations_url", "dtype": "string"}, {"name": "repos_url", "dtype": "string"}, {"name": "events_url", "dtype": "string"}, {"name": "received_events_url", "dtype": "string"}, {"name": "type", "dtype": "string"}, {"name": "site_admin", "dtype": "bool"}]}, {"name": "milestone", "struct": [{"name": "url", "dtype": "string"}, {"name": "html_url", "dtype": "string"}, {"name": "labels_url", "dtype": "string"}, {"name": "id", "dtype": "int64"}, {"name": "node_id", "dtype": "string"}, {"name": "number", "dtype": "int64"}, {"name": "title", "dtype": "string"}, {"name": "description", "dtype": "string"}, {"name": "creator", "struct": [{"name": "login", "dtype": "string"}, {"name": "id", "dtype": "int64"}, {"name": "node_id", "dtype": "string"}, {"name": "avatar_url", "dtype": "string"}, {"name": "gravatar_id", "dtype": "string"}, {"name": "url", "dtype": "string"}, {"name": "html_url", "dtype": "string"}, {"name": "followers_url", "dtype": "string"}, {"name": "following_url", "dtype": "string"}, {"name": "gists_url", "dtype": "string"}, {"name": "starred_url", "dtype": "string"}, {"name": "subscriptions_url", "dtype": "string"}, {"name": "organizations_url", "dtype": "string"}, {"name": "repos_url", "dtype": "string"}, {"name": "events_url", "dtype": "string"}, {"name": "received_events_url", "dtype": "string"}, {"name": "type", "dtype": "string"}, {"name": "site_admin", "dtype": "bool"}]}, {"name": "open_issues", "dtype": "int64"}, {"name": "closed_issues", "dtype": "int64"}, {"name": "state", "dtype": "string"}, {"name": "created_at", "dtype": "timestamp[s]"}, {"name": "updated_at", "dtype": "timestamp[s]"}, {"name": "due_on", "dtype": "null"}, {"name": "closed_at", "dtype": "null"}]}, {"name": "comments", "sequence": "string"}, {"name": "created_at", "dtype": "timestamp[s]"}, {"name": "updated_at", "dtype": "timestamp[s]"}, {"name": "closed_at", "dtype": "timestamp[s]"}, {"name": "author_association", "dtype": "string"}, {"name": "active_lock_reason", "dtype": "null"}, {"name": "body", "dtype": "string"}, {"name": "reactions", "struct": [{"name": "url", "dtype": "string"}, {"name": "total_count", "dtype": "int64"}, {"name": "+1", "dtype": "int64"}, {"name": "-1", "dtype": "int64"}, {"name": "laugh", "dtype": "int64"}, {"name": "hooray", "dtype": "int64"}, {"name": "confused", "dtype": "int64"}, {"name": "heart", "dtype": "int64"}, {"name": "rocket", "dtype": "int64"}, {"name": "eyes", "dtype": "int64"}]}, {"name": "timeline_url", "dtype": "string"}, {"name": "performed_via_github_app", "dtype": "null"}, {"name": "state_reason", "dtype": "string"}, {"name": "draft", "dtype": "bool"}, {"name": "pull_request", "struct": [{"name": "url", "dtype": "string"}, {"name": "html_url", "dtype": "string"}, {"name": "diff_url", "dtype": "string"}, {"name": "patch_url", "dtype": "string"}, {"name": "merged_at", "dtype": "timestamp[s]"}]}, {"name": "is_pull_request", "dtype": "bool"}], "splits": [{"name": "train", "num_bytes": 13501243, "num_examples": 1000}], "download_size": 3573221, "dataset_size": 13501243}, "configs": [{"config_name": "default", "data_files": [{"split": "train", "path": "data/train-*"}]}]} | 2023-11-30T01:30:09+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "github-issues"
More Information needed | [
"# Dataset Card for \"github-issues\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"github-issues\"\n\nMore Information needed"
] | [
6,
15
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"github-issues\"\n\nMore Information needed"
] |
1531b0ff62b959748e4595a1c3e3b865ec674225 |
Total train samples: 53959
Total test samples: 7347
Total tasks: 6
| Task | Train | Test |
| ---- | ----- | ---- |
|reference_number_association_without_question_boxes/2024-01-01|10009|2015|
|reference_numbers/2024-01-01|9586|856|
|reference_number_association_with_question_boxes/2024-01-01|7765|848|
|table_cell_incremental_without_question_boxes/2024-01-01|8456|797|
|table_cell_incremental_with_question_boxes/2024-01-01|8076|797|
|table_header_with_question_boxes/2024-01-01|10067|2034|
Total artifact_qids: 10482
| looppayments/question_answering_token_classification | [
"region:us"
] | 2023-11-30T02:11:46+00:00 | {"pretty_name": "Question Answering Token Classification"} | 2024-01-09T05:00:05+00:00 | [] | [] | TAGS
#region-us
| Total train samples: 53959
Total test samples: 7347
Total tasks: 6
Task: reference\_number\_association\_without\_question\_boxes/2024-01-01, Train: 10009, Test: 2015
Task: reference\_numbers/2024-01-01, Train: 9586, Test: 856
Task: reference\_number\_association\_with\_question\_boxes/2024-01-01, Train: 7765, Test: 848
Task: table\_cell\_incremental\_without\_question\_boxes/2024-01-01, Train: 8456, Test: 797
Task: table\_cell\_incremental\_with\_question\_boxes/2024-01-01, Train: 8076, Test: 797
Task: table\_header\_with\_question\_boxes/2024-01-01, Train: 10067, Test: 2034
Task: Total artifact\_qids: 10482, Train: , Test:
| [] | [
"TAGS\n#region-us \n"
] | [
6
] | [
"passage: TAGS\n#region-us \n"
] |
fb8f80e062323e574ab317e594940cfb84e27517 |
# Hands 2.7K
Approximately 2700 high quality, high resolution photos of human hands.
Captioned using CogVLM configured to return a maximum of 77 new tokens with the prompt:
```
Describe the image accurately and concisely, with few fill words.
```
Used a single A100-80G (37G VRAM consumed) at a batch size of 1 as CogVLM does not currently support batched inputs.
Used 3 seconds per image, 500 images every 25 minutes.
A small subset of a dataset of 18k images, this seemed to be enough to prove the concept while finishing in a reasonable period of time.
## Usage
The captions are filenames. Use a simple python script to convert them into .txt files if needed - strip the underscores, replacing them with spaces. | ptx0/hands-2.7k | [
"license:openrail",
"region:us"
] | 2023-11-30T03:14:56+00:00 | {"license": "openrail"} | 2023-11-30T03:21:48+00:00 | [] | [] | TAGS
#license-openrail #region-us
|
# Hands 2.7K
Approximately 2700 high quality, high resolution photos of human hands.
Captioned using CogVLM configured to return a maximum of 77 new tokens with the prompt:
Used a single A100-80G (37G VRAM consumed) at a batch size of 1 as CogVLM does not currently support batched inputs.
Used 3 seconds per image, 500 images every 25 minutes.
A small subset of a dataset of 18k images, this seemed to be enough to prove the concept while finishing in a reasonable period of time.
## Usage
The captions are filenames. Use a simple python script to convert them into .txt files if needed - strip the underscores, replacing them with spaces. | [
"# Hands 2.7K\n\nApproximately 2700 high quality, high resolution photos of human hands.\n\nCaptioned using CogVLM configured to return a maximum of 77 new tokens with the prompt:\n\n\n\nUsed a single A100-80G (37G VRAM consumed) at a batch size of 1 as CogVLM does not currently support batched inputs.\n\nUsed 3 seconds per image, 500 images every 25 minutes.\n\nA small subset of a dataset of 18k images, this seemed to be enough to prove the concept while finishing in a reasonable period of time.",
"## Usage\n\nThe captions are filenames. Use a simple python script to convert them into .txt files if needed - strip the underscores, replacing them with spaces."
] | [
"TAGS\n#license-openrail #region-us \n",
"# Hands 2.7K\n\nApproximately 2700 high quality, high resolution photos of human hands.\n\nCaptioned using CogVLM configured to return a maximum of 77 new tokens with the prompt:\n\n\n\nUsed a single A100-80G (37G VRAM consumed) at a batch size of 1 as CogVLM does not currently support batched inputs.\n\nUsed 3 seconds per image, 500 images every 25 minutes.\n\nA small subset of a dataset of 18k images, this seemed to be enough to prove the concept while finishing in a reasonable period of time.",
"## Usage\n\nThe captions are filenames. Use a simple python script to convert them into .txt files if needed - strip the underscores, replacing them with spaces."
] | [
12,
126,
42
] | [
"passage: TAGS\n#license-openrail #region-us \n# Hands 2.7K\n\nApproximately 2700 high quality, high resolution photos of human hands.\n\nCaptioned using CogVLM configured to return a maximum of 77 new tokens with the prompt:\n\n\n\nUsed a single A100-80G (37G VRAM consumed) at a batch size of 1 as CogVLM does not currently support batched inputs.\n\nUsed 3 seconds per image, 500 images every 25 minutes.\n\nA small subset of a dataset of 18k images, this seemed to be enough to prove the concept while finishing in a reasonable period of time.## Usage\n\nThe captions are filenames. Use a simple python script to convert them into .txt files if needed - strip the underscores, replacing them with spaces."
] |
6781e8decd192e20e588a09b6a21f17e0f661c9a | BioNet contains the raw data for the building the graph augmented LLMs
---
license: mit
---
| Zehui127127/BioNet | [
"region:us"
] | 2023-11-30T03:25:38+00:00 | {} | 2023-11-30T05:09:56+00:00 | [] | [] | TAGS
#region-us
| BioNet contains the raw data for the building the graph augmented LLMs
---
license: mit
---
| [] | [
"TAGS\n#region-us \n"
] | [
6
] | [
"passage: TAGS\n#region-us \n"
] |
429d3dd237c3140a5bb3ede485408c92017e4a96 | # Dataset Card for "Text2Speech_LJSpeech"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | DynamicSuperb/Text2Speech_LJSpeech | [
"region:us"
] | 2023-11-30T03:44:32+00:00 | {"configs": [{"config_name": "default", "data_files": [{"split": "test", "path": "data/test-*"}]}], "dataset_info": {"features": [{"name": "file", "dtype": "string"}, {"name": "text", "dtype": "string"}, {"name": "reference_speech_id", "dtype": "string"}, {"name": "reference_speech", "dtype": {"audio": {"sampling_rate": 22050}}}, {"name": "reference_speech_transcription", "dtype": "string"}, {"name": "label", "dtype": {"audio": {"sampling_rate": 22050}}}, {"name": "instruction", "dtype": "string"}], "splits": [{"name": "test", "num_bytes": 7684795920.0, "num_examples": 13100}], "download_size": 7562872204, "dataset_size": 7684795920.0}} | 2023-11-30T03:56:49+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "Text2Speech_LJSpeech"
More Information needed | [
"# Dataset Card for \"Text2Speech_LJSpeech\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"Text2Speech_LJSpeech\"\n\nMore Information needed"
] | [
6,
20
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"Text2Speech_LJSpeech\"\n\nMore Information needed"
] |
951f8f8a06175aa09e831aa815e800f6e85f2f8b | # Dataset Card for "sst2_non_affix_neg"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | joey234/sst2_non_affix_neg | [
"region:us"
] | 2023-11-30T03:44:44+00:00 | {"dataset_info": {"features": [{"name": "idx", "dtype": "int32"}, {"name": "sentence", "dtype": "string"}, {"name": "label", "dtype": {"class_label": {"names": {"0": "negative", "1": "positive"}}}}], "splits": [{"name": "validation", "num_bytes": 98088.14220183487, "num_examples": 805}], "download_size": 66484, "dataset_size": 98088.14220183487}, "configs": [{"config_name": "default", "data_files": [{"split": "validation", "path": "data/validation-*"}]}]} | 2023-11-30T03:44:47+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "sst2_non_affix_neg"
More Information needed | [
"# Dataset Card for \"sst2_non_affix_neg\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"sst2_non_affix_neg\"\n\nMore Information needed"
] | [
6,
21
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"sst2_non_affix_neg\"\n\nMore Information needed"
] |
6dfee6b5b1b93c48373786ac4f3a6a0df8fed4c5 | # Evolution instructions
Originally from https://github.com/nlpxucan/WizardLM/tree/main/Evol_Instruct, added some prompts to become malaysian context.
Generated using ChatGPT3.5, notebooks at https://github.com/mesolitica/malaysian-dataset/tree/master/chatbot/evol-instruct
## Alpaca Evolution
We use https://raw.githubusercontent.com/gururise/AlpacaDataCleaned/main/alpaca_data_cleaned.json and evolve using Evolution Instruction.
- [synthetic-alpaca_data_cleaned.jsonl](synthetic-alpaca_data_cleaned.jsonl), 51738 rows, 152 MB.
### Example data
```python
{'instruction': 'Beri tiga petua untuk menjaga kesihatan yang sepadan di negara Malaysia.',
'output': 'Tiga petua untuk menjaga kesihatan yang sepadan di negara Malaysia adalah:\n1. Makan makanan yang seimbang dan berkhasiat: Berusaha untuk mengamalkan pemakanan yang seimbang dengan menggabungkan semua kumpulan makanan seperti bijirin, sayur-sayuran, buah-buahan, protein dan lemak yang sihat. Hindari makanan yang tinggi gula, garam, dan lemak tepu. Pastikan bahawa makanan yang diambil adalah segar dan bersih.\n2. Budayakan senaman secara berkala: Amalkan senaman secara teratur seperti berjalan kaki, berlari, berenang, atau mengikuti kelas senaman. Senaman dapat membantu mengurangkan risiko penyakit jantung, diabetes, obesiti, dan meningkatkan kesihatan mental dan fizikal. Pastikan anda mendapatkan cahaya matahari yang mencukupi untuk memperoleh vitamin D yang penting bagi kesihatan tulang.\n3. Amalkan gaya hidup sihat: Hindari merokok dan minum alkohol. Jarakkan diri dari aktiviti yang berisiko seperti penggunaan dadah terlarang. Pastikan tidur yang mencukupi untuk pemulihan tubuh dan minda yang optimum. Perhatikan kesihatan mental dengan melakukan aktiviti yang menyenangkan seperti meditasi, mengurus stres dan mencari sokongan sosial daripada keluarga atau rakan sejawat.\n\nTindakan ini boleh membantu meningkatkan kesihatan dan kualiti hidup anda di negara Malaysia.',
'indon_ins': False,
'indon_output': False,
'instruction_ms': 'Berikan tiga petua untuk menjaga kesihatan yang sesuai di negara Malaysia.',
'output_ms': 'Tiga petua untuk menjaga kesihatan yang sepadan di Malaysia ialah:\n1. Makan makanan yang seimbang dan berkhasiat: Cuba mengamalkan pemakanan yang seimbang dengan menggabungkan semua kumpulan makanan seperti bijirin, sayur-sayuran, buah-buahan, protein dan lemak yang sihat. Elakkan makanan yang tinggi gula, garam, dan lemak tepu. Pastikan makanan yang diambil adalah segar dan bersih.\n2. Budayakan senaman secara berkala: Amalkan senaman secara teratur seperti berjalan kaki, berlari, berenang, atau mengikuti kelas senaman. Senaman boleh membantu mengurangkan risiko penyakit jantung, diabetes, obesiti, dan meningkatkan kesihatan mental dan fizikal. Pastikan anda mendapat cahaya matahari yang mencukupi untuk mendapatkan vitamin D yang penting untuk kesihatan tulang.\n3. Amalkan gaya hidup sihat: Elakkan merokok dan minum alkohol. Jauhi aktiviti yang berisiko seperti penggunaan dadah terlarang. Pastikan tidur yang mencukupi untuk pemulihan badan dan minda yang optimum. Perhatikan kesihatan mental dengan melakukan aktiviti yang menyenangkan seperti meditasi, menguruskan tekanan dan mencari sokongan sosial daripada keluarga atau rakan sejawat.\n\nTindakan ini boleh membantu meningkatkan kesihatan dan kualiti hidup anda di Malaysia.',
'rejected_ins': False,
'rejected_output': False}
```
## Code Evolution
We use https://huggingface.co/datasets/TokenBender/unnatural_code_instructions_20M and evolve using Evolution Instruction.
- [synthetic-code-instructions.jsonl](synthetic-code-instructions.jsonl), 111920 rows, 462 MB.
### Example data
```python
{'instruction': 'Tulis kod Python untuk menginisialisasi matriks 100 x 100 dengan nilai integer acak yang berkisar dari -100 hingga 100, tetapi pastikan bahwa jumlah nilai dalam setiap baris sama dengan nilai target tertentu.\n\nNilai target harus menjadi integer acak yang berkisar dari -1000 hingga 1000, dan harus berbeda untuk setiap baris.',
'output': 'Berikut adalah contoh kode Python untuk menginisialisasi matriks 100 x 100 dengan nilai integer acak yang memenuhi persyaratan yang Anda berikan:\n\n```python\nimport random\n\ndef inisialisasi_matriks():\n matriks = []\n for _ in range(100):\n target = random.randint(-1000, 1000)\n baris = []\n while sum(baris) != target:\n baris = [random.randint(-100, 100) for _ in range(100)]\n matriks.append(baris)\n return matriks\n\n# Contoh pemanggilan fungsi\nmatriks = inisialisasi_matriks()\n\n# Menampilkan matriks\nfor baris in matriks:\n print(baris)\n```\n\nKode di atas menggunakan perulangan untuk menginisialisasi setiap baris dalam matriks. Di setiap iterasi, kode akan memilih nilai target secara acak menggunakan fungsi `random.randint()` dengan rentang dari -1000 hingga 1000. Kemudian, kode akan menghasilkan baris acak dengan menggunakan list comprehension dan memastikan bahwa jumlah nilai dalam baris sama dengan nilai target. Jika jumlah nilai dalam baris tidak sesuai dengan nilai target, maka baris akan diperbarui hingga memenuhi syarat tersebut.\n\nSilakan gunakan dan modifikasi kode tersebut sesuai dengan kebutuhan Anda.',
'indon_ins': True,
'indon_output': True,
'instruction_ms': 'Tulis kod Python untuk memulakan matriks 100 x 100 dengan nilai integer rawak yang berkisar antara -100 hingga 100, tetapi pastikan jumlah nilai dalam setiap baris adalah sama dengan nilai sasaran tertentu.\n\nNilai sasaran mestilah integer rawak yang berkisar antara -1000 hingga 1000, dan mestilah berbeza untuk setiap baris.',
'output_ms': 'Berikut adalah contoh kod Python untuk memulakan matriks 100 x 100 dengan nilai integer rawak yang memenuhi keperluan yang anda berikan:\n\n```python\nimport random\n\ndef initialization_matrix():\n matrix = []\n for _ in range(100):\n target = random.randint(-1000, 1000)\n line = []\n while sum(row)!= target:\n line = [random.randint(-100, 100) for _ in range(100)]\n matrix.append(row)\n return matrix\n\n# Contoh panggilan fungsi\nmatrix = initialization_matrix()\n\n# Papar matrix\nfor row in matrix:\n print(row)\n```\n\nKod di atas menggunakan pengulangan untuk memulakan setiap baris dalam matriks. Dalam setiap iterasi, kod akan memilih nilai sasaran secara rawak menggunakan fungsi `random.randint()` dengan julat dari -1000 hingga 1000. Kemudian, kod akan menghasilkan baris rawak menggunakan senarai pemahaman dan memastikan jumlah nilai dalam baris sama dengan nilai sasaran. Jika jumlah nilai dalam baris tidak sepadan dengan nilai sasaran, maka baris akan dikemas kini sehingga memenuhi syarat tersebut.\n\nSila gunakan dan ubah kod mengikut keperluan anda.',
'rejected_ins': False,
'rejected_output': False}
```
## Malaysian Evolution
We use https://huggingface.co/datasets/mesolitica/chatgpt4-malaysian-general-qa and evolve using Evolution Instruction.
- [synthetic-evol-instructions.jsonl](synthetic-evol-instructions.jsonl), 104286 rows, 365 MB.
- [synthetic-malaysian-general-qa.jsonl](synthetic-malaysian-general-qa.jsonl), 25652 rows, 77.1 MB.
- [synthetic-malaysian-general-qa-v2.jsonl](synthetic-malaysian-general-qa-v2.jsonl), 22513 rows, 89.2 MB.
### Example data
```python
{'instruction': 'Dapatkah anda membuat suatu versi yang diperbaharui daripada ayat yang memberi fokus kepada kepentingan kecocokan budaya dalam penilaian calon? \n\nMemang, saya memahami tanggungjawab jawatan ini dan bersedia untuk menganalisis serta mengkaji kecekapan teknikal dan kebolehan komunikasi calon dengan cekap, memberikan maklum balas yang bernas terhadap jawapan mereka, dan memberikan cadangan yang mendalam berkenaan kesesuaian mereka dengan jawatan tersebut.',
'output': 'Tentu, berikut ini adalah versi yang diperbaharui daripada ayat yang lebih memberi fokus kepada kepentingan kecocokan budaya dalam penilaian calon:\n\n"Saya menaruh perhatian yang besar terhadap pentingnya kecocokan budaya dalam menilai calon. Saya sepenuhnya memahami tanggung jawab jabatan ini dan siap untuk menganalisis dan mengevaluasi secara teliti keahlian teknis dan kemampuan komunikasi calon. Saya akan memberikan tanggapan yang mendalam terhadap jawaban mereka dan memberikan saran yang relevan mengenai kesesuaian mereka dengan jabatan ini."',
'indon_ins': False,
'indon_output': True,
'instruction_ms': 'Bolehkah anda membuat versi yang diperbaharui daripada ayat yang memberi tumpuan kepada kepentingan kecocokan budaya dalam penilaian calon?\n\nMemang, saya memahami tanggungjawab jawatan ini dan bersedia untuk menganalisis serta mengkaji kecekapan teknikal dan kebolehan komunikasi calon dengan cekap, memberikan maklum balas yang bernas terhadap jawapan mereka, dan memberikan cadangan yang mendalam berkenaan kesesuaian mereka dengan jawatan tersebut.',
'output_ms': 'Sudah tentu, berikut adalah versi yang diperbaharui daripada ayat yang lebih memberi tumpuan kepada kepentingan kesesuaian budaya dalam penilaian calon:\n\n"Saya memberi perhatian yang besar kepada kepentingan kesesuaian budaya dalam menilai calon. Saya sepenuhnya memahami tanggungjawab jawatan ini dan bersedia untuk menganalisis dan menilai dengan teliti kepakaran teknikal dan keupayaan komunikasi calon. Saya akan memberikan jawapan yang mendalam terhadap jawapan mereka dan memberikan nasihat yang relevan tentang kesesuaian mereka dengan jawatan ini."',
'rejected_ins': False,
'rejected_output': False}
```
## Malay glaive_coder_raw_text
Translate instructions from https://huggingface.co/datasets/TokenBender/glaive_coder_raw_text and answer using ChatGPT3.5
We extend the dataset to become multi-turn at https://huggingface.co/datasets/mesolitica/chatgpt-code-instruct-multiturn
- [synthetic-glaive_coder_raw_text.jsonl](synthetic-glaive_coder_raw_text.jsonl), 131091 rows, 460 MB.
### Example data
```python
{'instruction': 'Bagaimana cara untuk memasang Python 3 pada instans AWS EC2? Saya telah mencuba menggunakan arahan `sudo yum install python3`, tetapi saya menerima mesej ralat yang mengatakan `Tiada pakej python3 tersedia.`. Saya telah mencari dalam talian tetapi tidak menemui sebarang penyelesaian. Adakah saya perlu memuat turun dan memasangnya secara manual?',
'output': 'Untuk memasang Python 3 pada instans AWS EC2, anda boleh menggunakan arahan `yum` untuk memasang pakej yang diperlukan. Namun, cara terbaik untuk memasang Python 3 adalah dengan menggunakan EPEL (Extra Packages for Enterprise Linux) repository. Anda boleh menggunakan arahan berikut untuk memasang EPEL repository:\n\n```bash\nsudo yum install epel-release\n```\n\nSelepas itu, anda boleh memasang Python 3 dengan menggunakan arahan berikut:\n\n```bash\nsudo yum install python3\n```\n\nDengan langkah-langkah ini, anda seharusnya dapat memasang Python 3 dengan mudah pada instans AWS EC2 anda. Semoga berjaya!',
'instruction_en': "How can I install Python 3 on an AWS EC2 instance? I tried using the command `sudo yum install python3`, but I received an error message saying `No package python3 available.`. I searched online but didn't find a solution. Do I need to download and install it manually?",
'indon_ins': False,
'indon_output': False,
'instruction_ms': 'Bagaimana untuk memasang Python 3 pada AWS EC2 instance? Saya telah mencuba menggunakan arahan `sudo yum install python3`, tetapi saya menerima mesej ralat yang mengatakan `Tiada pakej python3 tersedia.`. Saya telah mencari dalam talian tetapi tidak menemui sebarang penyelesaian. Adakah saya perlu memuat turun dan memasangnya secara manual?',
'output_ms': 'Untuk memasang Python 3 pada instans AWS EC2, anda boleh menggunakan arahan `yum` untuk memasang pakej yang diperlukan. Walau bagaimanapun, cara terbaik untuk memasang Python 3 adalah dengan menggunakan repositori EPEL (Extra Packages for Enterprise Linux). Anda boleh menggunakan arahan berikut untuk memasang repositori EPEL:\n\n```bash\nsudo yum install epel-release\n```\n\nSelepas itu, anda boleh memasang Python 3 dengan menggunakan arahan berikut:\n\n```bash\nsudo yum install python3\n```\n\nDengan langkah-langkah ini, anda sepatutnya dapat memasang Python 3 dengan mudah pada instans AWS EC2 anda. Semoga berjaya!',
'rejected_ins': False,
'rejected_output': False}
```
## Malay Magicoder
Translate instructions from https://huggingface.co/datasets/ise-uiuc/Magicoder-OSS-Instruct-75K and answer using ChatGPT3.5
- [synthetic-oss_instruct-decontaminated.jsonl](synthetic-oss_instruct-decontaminated.jsonl), 70815 rows, 499 MB.
### Example data
```python
{'instruction': 'Anda diberi tugas untuk melaksanakan fungsi Python yang mudah yang mengambil senarai rentetan sebagai input dan mengembalikan senarai baru yang mengandungi hanya rentetan yang merupakan palindrom. Palindrom adalah perkataan, frasa, nombor, atau rentetan karakter lain yang dibaca sama dari kiri ke kanan dan dari kanan ke kiri (tanpa mengira ruang, tanda baca, dan huruf besar).\n\nAnda diberikan potongan kod berikut sebagai titik permulaan:\n\n```python\ndef find_palindromes(words):\n # Kod anda di sini\n return palindromes\n```\n\nPerkerjaan anda adalah melengkapkan fungsi `find_palindromes` untuk menapis palindrom dari senarai input rentetan dan mengembalikan senarai baru yang mengandungi hanya palindrom.\n\nSebagai contoh, jika senarai input adalah `["radar", "hello", "level", "world", "Anna"]`, fungsi tersebut harus mengembalikan `["radar", "level", "Anna"]`.',
'output': 'Anda boleh melengkapkan fungsi `find_palindromes` seperti berikut:\n\n```python\ndef find_palindromes(words):\n palindromes = []\n for word in words:\n # Mengabaikan ruang, tanda baca, dan mengubah huruf menjadi huruf kecil\n word = word.lower()\n word = word.replace(" ", "")\n word = \'\'.join(e for e in word if e.isalnum())\n\n # Memeriksa sama ada kata adalah palindrom\n if word == word[::-1]:\n palindromes.append(word)\n \n return palindromes\n```\n\nDalam kod di atas, kita menggunakan pemangkasan slice `[::-1]` untuk membalikkan string `word`. Kami memeriksa sama ada kata adalah palindrom dengan membandingkan kata dengan kata yang sudah dibalik. Jika kata adalah palindrom, kami tambahkan ke senarai `palindromes`.\n\nContoh penggunaan fungsi ini adalah seperti berikut:\n\n```python\ninput_words = ["radar", "hello", "level", "world", "Anna"]\nresult = find_palindromes(input_words)\nprint(result) # Output: ["radar", "level", "anna"]\n```\n\nSekiranya terdapat kata-kata dalam senarai input yang merupakan palindrom, fungsi ini akan mengembalikan senarai yang mengandungi hanya palindrom tersebut. Dalam contoh ini, `["radar", "level", "anna"]` adalah palindrom yang ditemui dalam senarai input, jadi itulah yang akan dikembalikan.',
'indon_ins': False,
'indon_output': False,
'instruction_ms': 'Anda diberi tugas untuk melaksanakan fungsi Python yang mudah yang mengambil senarai rentetan sebagai input dan mengembalikan senarai baru yang mengandungi hanya rentetan yang merupakan palindrom. Palindrom adalah perkataan, frasa, nombor, atau rentetan aksara lain yang dibaca sama dari kiri ke kanan dan dari kanan ke kiri (tanpa mengira ruang, tanda baca, dan huruf besar).\n\nAnda diberikan potongan kod berikut sebagai titik permulaan:\n\n```python\ndef find_palindromes(words):\n # Kod anda di sini\n return palindromes\n```\n\nKerja anda adalah melengkapkan fungsi `find_palindromes` untuk menyaring palindrom dari senarai input rentetan dan mengembalikan senarai baru yang mengandungi hanya palindrom.\n\nSebagai contoh, jika senarai input adalah `["radar", "hello", "level", "world", "Anna"]`, fungsi tersebut harus mengembalikan `["radar", "level", "Anna"]`.',
'output_ms': 'Anda boleh melengkapkan fungsi `find_palindromes` seperti berikut:\n\n```python\ndef find_palindromes(words):\n palindromes = []\n for word in words:\n # Mengabaikan ruang, tanda baca, dan menukar huruf kepada huruf kecil\n word = word.lower()\n word = word.replace(" ", "")\n word = \'\'.join(e for e in word if e.isalnum())\n\n # Memuji sama ada perkataan adalah palindrom\n if word == word[::-1]:\n palindromes.append(word)\n \n return palindromes\n```\n\nDalam kod di atas, kami menggunakan pemangkasan slice `[::-1]` untuk membalikkan rentetan `word`. Kami memeriksa sama ada perkataan adalah palindrom dengan membandingkan perkataan dengan perkataan yang telah dibalik. Jika perkataan adalah palindrom, kami menambahkannya ke dalam senarai `palindromes`.\n\nContoh penggunaan fungsi ini adalah seperti berikut:\n\n```python\ninput_words = ["radar", "hello", "level", "world", "Anna"]\nresult = find_palindromes(input_words)\nprint(result) # Output: ["radar", "level", "anna"]\n```\n\nJika terdapat perkataan dalam senarai input yang merupakan palindrom, fungsi ini akan mengembalikan senarai yang mengandungi hanya palindrom tersebut. Dalam contoh ini, `["radar", "level", "anna"]` adalah palindrom yang ditemui dalam senarai input, jadi itulah yang akan dikembalikan.',
'rejected_ins': False,
'rejected_output': False,
'instruction_en': 'You are tasked with implementing a simple Python function that takes a list of strings as input and returns a new list containing only the strings that are palindromes. A palindrome is a word, phrase, number, or other sequence of characters that reads the same forward and backward (ignoring spaces, punctuation, and capitalization).\n\nYou are provided with the following code snippet as a starting point:\n\n```python\ndef find_palindromes(words):\n # Your code here\n return palindromes\n```\n\nYour task is to complete the `find_palindromes` function to filter out the palindromes from the input list of strings and return a new list containing only the palindromes.\n\nFor example, if the input list is `["radar", "hello", "level", "world", "Anna"]`, the function should return `["radar", "level", "Anna"]`.'}
``` | mesolitica/chatgpt-malay-instructions | [
"language:ms",
"region:us"
] | 2023-11-30T03:45:48+00:00 | {"language": ["ms"], "pretty_name": "malay-instru"} | 2024-02-02T09:54:08+00:00 | [] | [
"ms"
] | TAGS
#language-Malay (macrolanguage) #region-us
| # Evolution instructions
Originally from URL added some prompts to become malaysian context.
Generated using ChatGPT3.5, notebooks at URL
## Alpaca Evolution
We use URL and evolve using Evolution Instruction.
- synthetic-alpaca_data_cleaned.jsonl, 51738 rows, 152 MB.
### Example data
## Code Evolution
We use URL and evolve using Evolution Instruction.
- URL, 111920 rows, 462 MB.
### Example data
python\nimport random\n\ndef inisialisasi_matriks():\n matriks = []\n for _ in range(100):\n target = random.randint(-1000, 1000)\n baris = []\n while sum(baris) != target:\n baris = [random.randint(-100, 100) for _ in range(100)]\n URL(baris)\n return matriks\n\n# Contoh pemanggilan fungsi\nmatriks = inisialisasi_matriks()\n\n# Menampilkan matriks\nfor baris in matriks:\n print(baris)\npython\nimport random\n\ndef initialization_matrix():\n matrix = []\n for _ in range(100):\n target = random.randint(-1000, 1000)\n line = []\n while sum(row)!= target:\n line = [random.randint(-100, 100) for _ in range(100)]\n URL(row)\n return matrix\n\n# Contoh panggilan fungsi\nmatrix = initialization_matrix()\n\n# Papar matrix\nfor row in matrix:\n print(row)\n
## Malaysian Evolution
We use URL and evolve using Evolution Instruction.
- URL, 104286 rows, 365 MB.
- URL, 25652 rows, 77.1 MB.
- URL, 22513 rows, 89.2 MB.
### Example data
## Malay glaive_coder_raw_text
Translate instructions from URL and answer using ChatGPT3.5
We extend the dataset to become multi-turn at URL
- synthetic-glaive_coder_raw_text.jsonl, 131091 rows, 460 MB.
### Example data
bash\nsudo yum install epel-release\nbash\nsudo yum install python3\nbash\nsudo yum install epel-release\nbash\nsudo yum install python3\n
## Malay Magicoder
Translate instructions from URL and answer using ChatGPT3.5
- synthetic-oss_instruct-URL, 70815 rows, 499 MB.
### Example data
python\ndef find_palindromes(words):\n # Kod anda di sini\n return palindromes\npython\ndef find_palindromes(words):\n palindromes = []\n for word in words:\n # Mengabaikan ruang, tanda baca, dan mengubah huruf menjadi huruf kecil\n word = URL()\n word = word.replace(" ", "")\n word = \'\'.join(e for e in word if e.isalnum())\n\n # Memeriksa sama ada kata adalah palindrom\n if word == word[::-1]:\n URL(word)\n \n return palindromes\npython\ninput_words = ["radar", "hello", "level", "world", "Anna"]\nresult = find_palindromes(input_words)\nprint(result) # Output: ["radar", "level", "anna"]\npython\ndef find_palindromes(words):\n # Kod anda di sini\n return palindromes\npython\ndef find_palindromes(words):\n palindromes = []\n for word in words:\n # Mengabaikan ruang, tanda baca, dan menukar huruf kepada huruf kecil\n word = URL()\n word = word.replace(" ", "")\n word = \'\'.join(e for e in word if e.isalnum())\n\n # Memuji sama ada perkataan adalah palindrom\n if word == word[::-1]:\n URL(word)\n \n return palindromes\npython\ninput_words = ["radar", "hello", "level", "world", "Anna"]\nresult = find_palindromes(input_words)\nprint(result) # Output: ["radar", "level", "anna"]\npython\ndef find_palindromes(words):\n # Your code here\n return palindromes\n | [
"# Evolution instructions\n\nOriginally from URL added some prompts to become malaysian context.\n\nGenerated using ChatGPT3.5, notebooks at URL",
"## Alpaca Evolution\n\nWe use URL and evolve using Evolution Instruction.\n\n- synthetic-alpaca_data_cleaned.jsonl, 51738 rows, 152 MB.",
"### Example data",
"## Code Evolution\n\nWe use URL and evolve using Evolution Instruction. \n\n- URL, 111920 rows, 462 MB.",
"### Example data\n\npython\\nimport random\\n\\ndef inisialisasi_matriks():\\n matriks = []\\n for _ in range(100):\\n target = random.randint(-1000, 1000)\\n baris = []\\n while sum(baris) != target:\\n baris = [random.randint(-100, 100) for _ in range(100)]\\n URL(baris)\\n return matriks\\n\\n# Contoh pemanggilan fungsi\\nmatriks = inisialisasi_matriks()\\n\\n# Menampilkan matriks\\nfor baris in matriks:\\n print(baris)\\npython\\nimport random\\n\\ndef initialization_matrix():\\n matrix = []\\n for _ in range(100):\\n target = random.randint(-1000, 1000)\\n line = []\\n while sum(row)!= target:\\n line = [random.randint(-100, 100) for _ in range(100)]\\n URL(row)\\n return matrix\\n\\n# Contoh panggilan fungsi\\nmatrix = initialization_matrix()\\n\\n# Papar matrix\\nfor row in matrix:\\n print(row)\\n",
"## Malaysian Evolution\n\nWe use URL and evolve using Evolution Instruction. \n\n- URL, 104286 rows, 365 MB.\n- URL, 25652 rows, 77.1 MB.\n- URL, 22513 rows, 89.2 MB.",
"### Example data",
"## Malay glaive_coder_raw_text\n\nTranslate instructions from URL and answer using ChatGPT3.5\n\nWe extend the dataset to become multi-turn at URL\n\n- synthetic-glaive_coder_raw_text.jsonl, 131091 rows, 460 MB.",
"### Example data\n\nbash\\nsudo yum install epel-release\\nbash\\nsudo yum install python3\\nbash\\nsudo yum install epel-release\\nbash\\nsudo yum install python3\\n",
"## Malay Magicoder\n\nTranslate instructions from URL and answer using ChatGPT3.5\n\n- synthetic-oss_instruct-URL, 70815 rows, 499 MB.",
"### Example data\n\npython\\ndef find_palindromes(words):\\n # Kod anda di sini\\n return palindromes\\npython\\ndef find_palindromes(words):\\n palindromes = []\\n for word in words:\\n # Mengabaikan ruang, tanda baca, dan mengubah huruf menjadi huruf kecil\\n word = URL()\\n word = word.replace(\" \", \"\")\\n word = \\'\\'.join(e for e in word if e.isalnum())\\n\\n # Memeriksa sama ada kata adalah palindrom\\n if word == word[::-1]:\\n URL(word)\\n \\n return palindromes\\npython\\ninput_words = [\"radar\", \"hello\", \"level\", \"world\", \"Anna\"]\\nresult = find_palindromes(input_words)\\nprint(result) # Output: [\"radar\", \"level\", \"anna\"]\\npython\\ndef find_palindromes(words):\\n # Kod anda di sini\\n return palindromes\\npython\\ndef find_palindromes(words):\\n palindromes = []\\n for word in words:\\n # Mengabaikan ruang, tanda baca, dan menukar huruf kepada huruf kecil\\n word = URL()\\n word = word.replace(\" \", \"\")\\n word = \\'\\'.join(e for e in word if e.isalnum())\\n\\n # Memuji sama ada perkataan adalah palindrom\\n if word == word[::-1]:\\n URL(word)\\n \\n return palindromes\\npython\\ninput_words = [\"radar\", \"hello\", \"level\", \"world\", \"Anna\"]\\nresult = find_palindromes(input_words)\\nprint(result) # Output: [\"radar\", \"level\", \"anna\"]\\npython\\ndef find_palindromes(words):\\n # Your code here\\n return palindromes\\n"
] | [
"TAGS\n#language-Malay (macrolanguage) #region-us \n",
"# Evolution instructions\n\nOriginally from URL added some prompts to become malaysian context.\n\nGenerated using ChatGPT3.5, notebooks at URL",
"## Alpaca Evolution\n\nWe use URL and evolve using Evolution Instruction.\n\n- synthetic-alpaca_data_cleaned.jsonl, 51738 rows, 152 MB.",
"### Example data",
"## Code Evolution\n\nWe use URL and evolve using Evolution Instruction. \n\n- URL, 111920 rows, 462 MB.",
"### Example data\n\npython\\nimport random\\n\\ndef inisialisasi_matriks():\\n matriks = []\\n for _ in range(100):\\n target = random.randint(-1000, 1000)\\n baris = []\\n while sum(baris) != target:\\n baris = [random.randint(-100, 100) for _ in range(100)]\\n URL(baris)\\n return matriks\\n\\n# Contoh pemanggilan fungsi\\nmatriks = inisialisasi_matriks()\\n\\n# Menampilkan matriks\\nfor baris in matriks:\\n print(baris)\\npython\\nimport random\\n\\ndef initialization_matrix():\\n matrix = []\\n for _ in range(100):\\n target = random.randint(-1000, 1000)\\n line = []\\n while sum(row)!= target:\\n line = [random.randint(-100, 100) for _ in range(100)]\\n URL(row)\\n return matrix\\n\\n# Contoh panggilan fungsi\\nmatrix = initialization_matrix()\\n\\n# Papar matrix\\nfor row in matrix:\\n print(row)\\n",
"## Malaysian Evolution\n\nWe use URL and evolve using Evolution Instruction. \n\n- URL, 104286 rows, 365 MB.\n- URL, 25652 rows, 77.1 MB.\n- URL, 22513 rows, 89.2 MB.",
"### Example data",
"## Malay glaive_coder_raw_text\n\nTranslate instructions from URL and answer using ChatGPT3.5\n\nWe extend the dataset to become multi-turn at URL\n\n- synthetic-glaive_coder_raw_text.jsonl, 131091 rows, 460 MB.",
"### Example data\n\nbash\\nsudo yum install epel-release\\nbash\\nsudo yum install python3\\nbash\\nsudo yum install epel-release\\nbash\\nsudo yum install python3\\n",
"## Malay Magicoder\n\nTranslate instructions from URL and answer using ChatGPT3.5\n\n- synthetic-oss_instruct-URL, 70815 rows, 499 MB.",
"### Example data\n\npython\\ndef find_palindromes(words):\\n # Kod anda di sini\\n return palindromes\\npython\\ndef find_palindromes(words):\\n palindromes = []\\n for word in words:\\n # Mengabaikan ruang, tanda baca, dan mengubah huruf menjadi huruf kecil\\n word = URL()\\n word = word.replace(\" \", \"\")\\n word = \\'\\'.join(e for e in word if e.isalnum())\\n\\n # Memeriksa sama ada kata adalah palindrom\\n if word == word[::-1]:\\n URL(word)\\n \\n return palindromes\\npython\\ninput_words = [\"radar\", \"hello\", \"level\", \"world\", \"Anna\"]\\nresult = find_palindromes(input_words)\\nprint(result) # Output: [\"radar\", \"level\", \"anna\"]\\npython\\ndef find_palindromes(words):\\n # Kod anda di sini\\n return palindromes\\npython\\ndef find_palindromes(words):\\n palindromes = []\\n for word in words:\\n # Mengabaikan ruang, tanda baca, dan menukar huruf kepada huruf kecil\\n word = URL()\\n word = word.replace(\" \", \"\")\\n word = \\'\\'.join(e for e in word if e.isalnum())\\n\\n # Memuji sama ada perkataan adalah palindrom\\n if word == word[::-1]:\\n URL(word)\\n \\n return palindromes\\npython\\ninput_words = [\"radar\", \"hello\", \"level\", \"world\", \"Anna\"]\\nresult = find_palindromes(input_words)\\nprint(result) # Output: [\"radar\", \"level\", \"anna\"]\\npython\\ndef find_palindromes(words):\\n # Your code here\\n return palindromes\\n"
] | [
16,
29,
41,
5,
26,
309,
53,
5,
66,
52,
41,
509
] | [
"passage: TAGS\n#language-Malay (macrolanguage) #region-us \n# Evolution instructions\n\nOriginally from URL added some prompts to become malaysian context.\n\nGenerated using ChatGPT3.5, notebooks at URL## Alpaca Evolution\n\nWe use URL and evolve using Evolution Instruction.\n\n- synthetic-alpaca_data_cleaned.jsonl, 51738 rows, 152 MB.### Example data## Code Evolution\n\nWe use URL and evolve using Evolution Instruction. \n\n- URL, 111920 rows, 462 MB.### Example data\n\npython\\nimport random\\n\\ndef inisialisasi_matriks():\\n matriks = []\\n for _ in range(100):\\n target = random.randint(-1000, 1000)\\n baris = []\\n while sum(baris) != target:\\n baris = [random.randint(-100, 100) for _ in range(100)]\\n URL(baris)\\n return matriks\\n\\n# Contoh pemanggilan fungsi\\nmatriks = inisialisasi_matriks()\\n\\n# Menampilkan matriks\\nfor baris in matriks:\\n print(baris)\\npython\\nimport random\\n\\ndef initialization_matrix():\\n matrix = []\\n for _ in range(100):\\n target = random.randint(-1000, 1000)\\n line = []\\n while sum(row)!= target:\\n line = [random.randint(-100, 100) for _ in range(100)]\\n URL(row)\\n return matrix\\n\\n# Contoh panggilan fungsi\\nmatrix = initialization_matrix()\\n\\n# Papar matrix\\nfor row in matrix:\\n print(row)\\n## Malaysian Evolution\n\nWe use URL and evolve using Evolution Instruction. \n\n- URL, 104286 rows, 365 MB.\n- URL, 25652 rows, 77.1 MB.\n- URL, 22513 rows, 89.2 MB.### Example data",
"passage: ## Malay glaive_coder_raw_text\n\nTranslate instructions from URL and answer using ChatGPT3.5\n\nWe extend the dataset to become multi-turn at URL\n\n- synthetic-glaive_coder_raw_text.jsonl, 131091 rows, 460 MB.### Example data\n\nbash\\nsudo yum install epel-release\\nbash\\nsudo yum install python3\\nbash\\nsudo yum install epel-release\\nbash\\nsudo yum install python3\\n## Malay Magicoder\n\nTranslate instructions from URL and answer using ChatGPT3.5\n\n- synthetic-oss_instruct-URL, 70815 rows, 499 MB."
] |
8f1b2e909565567150b4667f24ea61dfe0961d89 | # Dataset Card for "Text2Speech_LibriTTS-TestClean"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | DynamicSuperb/Text2Speech_LibriTTS-TestClean | [
"region:us"
] | 2023-11-30T03:58:18+00:00 | {"configs": [{"config_name": "default", "data_files": [{"split": "test", "path": "data/test-*"}]}], "dataset_info": {"features": [{"name": "file", "dtype": "string"}, {"name": "text", "dtype": "string"}, {"name": "reference_speech_id", "dtype": "string"}, {"name": "reference_speech", "dtype": {"audio": {"sampling_rate": 24000}}}, {"name": "reference_speech_transcription", "dtype": "string"}, {"name": "label", "dtype": {"audio": {"sampling_rate": 24000}}}, {"name": "instruction", "dtype": "string"}], "splits": [{"name": "test", "num_bytes": 2639185705.032, "num_examples": 4916}], "download_size": 2199786738, "dataset_size": 2639185705.032}} | 2023-11-30T04:00:14+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "Text2Speech_LibriTTS-TestClean"
More Information needed | [
"# Dataset Card for \"Text2Speech_LibriTTS-TestClean\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"Text2Speech_LibriTTS-TestClean\"\n\nMore Information needed"
] | [
6,
24
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"Text2Speech_LibriTTS-TestClean\"\n\nMore Information needed"
] |
226114cadde4f1cd72a81bb5e56d0c11a4f62316 | # Dataset Card for "Text2Speech_LibriTTS-TestOther"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | DynamicSuperb/Text2Speech_LibriTTS-TestOther | [
"region:us"
] | 2023-11-30T04:02:54+00:00 | {"configs": [{"config_name": "default", "data_files": [{"split": "test", "path": "data/test-*"}]}], "dataset_info": {"features": [{"name": "file", "dtype": "string"}, {"name": "text", "dtype": "string"}, {"name": "reference_speech_id", "dtype": "string"}, {"name": "reference_speech", "dtype": {"audio": {"sampling_rate": 24000}}}, {"name": "reference_speech_transcription", "dtype": "string"}, {"name": "label", "dtype": {"audio": {"sampling_rate": 24000}}}, {"name": "instruction", "dtype": "string"}], "splits": [{"name": "test", "num_bytes": 2825650487.816, "num_examples": 4892}], "download_size": 1538348109, "dataset_size": 2825650487.816}} | 2023-11-30T04:05:26+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "Text2Speech_LibriTTS-TestOther"
More Information needed | [
"# Dataset Card for \"Text2Speech_LibriTTS-TestOther\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"Text2Speech_LibriTTS-TestOther\"\n\nMore Information needed"
] | [
6,
24
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"Text2Speech_LibriTTS-TestOther\"\n\nMore Information needed"
] |
f9ced6f34ad04040ff60341a4bfa89480c215181 | # Dataset Card for "must-c-en-fr-wait03_21.6"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | maxolotl/must-c-en-fr-wait03_21.6 | [
"region:us"
] | 2023-11-30T05:06:58+00:00 | {"dataset_info": {"features": [{"name": "current_source", "dtype": "string"}, {"name": "current_target", "dtype": "string"}, {"name": "target_token", "dtype": "string"}], "splits": [{"name": "train", "num_bytes": 1054493511, "num_examples": 5459617}, {"name": "test", "num_bytes": 11657954, "num_examples": 63342}, {"name": "validation", "num_bytes": 5516382, "num_examples": 28830}], "download_size": 188781313, "dataset_size": 1071667847}} | 2023-11-30T05:07:22+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "must-c-en-fr-wait03_21.6"
More Information needed | [
"# Dataset Card for \"must-c-en-fr-wait03_21.6\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"must-c-en-fr-wait03_21.6\"\n\nMore Information needed"
] | [
6,
25
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"must-c-en-fr-wait03_21.6\"\n\nMore Information needed"
] |
cda0aaded760a2b2a05dd908984e80d01a0ac0fa | # Dataset Card for "must-c-en-fr-wait05_21.7"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | maxolotl/must-c-en-fr-wait05_21.7 | [
"region:us"
] | 2023-11-30T05:07:32+00:00 | {"dataset_info": {"features": [{"name": "current_source", "dtype": "string"}, {"name": "current_target", "dtype": "string"}, {"name": "target_token", "dtype": "string"}], "splits": [{"name": "train", "num_bytes": 1100095602, "num_examples": 5459617}, {"name": "test", "num_bytes": 12172258, "num_examples": 63342}, {"name": "validation", "num_bytes": 5754906, "num_examples": 28830}], "download_size": 185590783, "dataset_size": 1118022766}} | 2023-11-30T05:07:52+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "must-c-en-fr-wait05_21.7"
More Information needed | [
"# Dataset Card for \"must-c-en-fr-wait05_21.7\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"must-c-en-fr-wait05_21.7\"\n\nMore Information needed"
] | [
6,
25
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"must-c-en-fr-wait05_21.7\"\n\nMore Information needed"
] |
29a3e985985f03f7b54d0e99feb225b67eb7680e | # Dataset Card for "must-c-en-fr-wait07_21.8"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | maxolotl/must-c-en-fr-wait07_21.8 | [
"region:us"
] | 2023-11-30T05:08:03+00:00 | {"dataset_info": {"features": [{"name": "current_source", "dtype": "string"}, {"name": "current_target", "dtype": "string"}, {"name": "target_token", "dtype": "string"}], "splits": [{"name": "train", "num_bytes": 1140444988, "num_examples": 5459617}, {"name": "test", "num_bytes": 12622881, "num_examples": 63342}, {"name": "validation", "num_bytes": 5965971, "num_examples": 28830}], "download_size": 181926664, "dataset_size": 1159033840}} | 2023-11-30T05:08:24+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "must-c-en-fr-wait07_21.8"
More Information needed | [
"# Dataset Card for \"must-c-en-fr-wait07_21.8\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"must-c-en-fr-wait07_21.8\"\n\nMore Information needed"
] | [
6,
25
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"must-c-en-fr-wait07_21.8\"\n\nMore Information needed"
] |
28d29e9fe7c3147141af55a51fe079aa29cd0bad | # Dataset Card for "must-c-en-fr-wait09_21.8"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | maxolotl/must-c-en-fr-wait09_21.8 | [
"region:us"
] | 2023-11-30T05:08:34+00:00 | {"dataset_info": {"features": [{"name": "current_source", "dtype": "string"}, {"name": "current_target", "dtype": "string"}, {"name": "target_token", "dtype": "string"}], "splits": [{"name": "train", "num_bytes": 1175723805, "num_examples": 5459617}, {"name": "test", "num_bytes": 13012390, "num_examples": 63342}, {"name": "validation", "num_bytes": 6150851, "num_examples": 28830}], "download_size": 178232913, "dataset_size": 1194887046}} | 2023-11-30T05:08:54+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "must-c-en-fr-wait09_21.8"
More Information needed | [
"# Dataset Card for \"must-c-en-fr-wait09_21.8\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"must-c-en-fr-wait09_21.8\"\n\nMore Information needed"
] | [
6,
25
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"must-c-en-fr-wait09_21.8\"\n\nMore Information needed"
] |
6d956f2c5b810bfaed91f4846e144412ebc9a95f | # Dataset Card for "must-c-en-fr_21.8"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | maxolotl/must-c-en-fr_21.8 | [
"region:us"
] | 2023-11-30T05:08:56+00:00 | {"dataset_info": {"features": [{"name": "en", "dtype": "string"}, {"name": "fr", "dtype": "string"}], "splits": [{"name": "train", "num_bytes": 61411559, "num_examples": 268645}, {"name": "test", "num_bytes": 697604, "num_examples": 3165}, {"name": "validation", "num_bytes": 321473, "num_examples": 1403}], "download_size": 37992225, "dataset_size": 62430636}} | 2023-11-30T05:09:04+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "must-c-en-fr_21.8"
More Information needed | [
"# Dataset Card for \"must-c-en-fr_21.8\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"must-c-en-fr_21.8\"\n\nMore Information needed"
] | [
6,
21
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"must-c-en-fr_21.8\"\n\nMore Information needed"
] |
57e598ab651b64d2166951818cc746098117ff9f | # Dataset Card for "random25eof_find_passage_train1000_eval100_rare_train_qa_in_validation"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | tyzhu/random25eof_find_passage_train1000_eval100_rare_train_qa_in_validation | [
"region:us"
] | 2023-11-30T06:33:48+00:00 | {"configs": [{"config_name": "default", "data_files": [{"split": "train", "path": "data/train-*"}, {"split": "validation", "path": "data/validation-*"}]}], "dataset_info": {"features": [{"name": "inputs", "dtype": "string"}, {"name": "targets", "dtype": "string"}], "splits": [{"name": "train", "num_bytes": 219292, "num_examples": 2100}, {"name": "validation", "num_bytes": 115598.0, "num_examples": 1100}], "download_size": 141935, "dataset_size": 334890.0}} | 2023-11-30T06:33:59+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "random25eof_find_passage_train1000_eval100_rare_train_qa_in_validation"
More Information needed | [
"# Dataset Card for \"random25eof_find_passage_train1000_eval100_rare_train_qa_in_validation\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"random25eof_find_passage_train1000_eval100_rare_train_qa_in_validation\"\n\nMore Information needed"
] | [
6,
41
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"random25eof_find_passage_train1000_eval100_rare_train_qa_in_validation\"\n\nMore Information needed"
] |
87a39b9087b74db82306c9835edba1edb4805d5d | # Dataset Card for "find_first_sent_train_100_eval_40_recite"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | tyzhu/find_first_sent_train_100_eval_40_recite | [
"region:us"
] | 2023-11-30T07:03:34+00:00 | {"configs": [{"config_name": "default", "data_files": [{"split": "train", "path": "data/train-*"}, {"split": "validation", "path": "data/validation-*"}]}], "dataset_info": {"features": [{"name": "inputs", "dtype": "string"}, {"name": "targets", "dtype": "string"}, {"name": "title", "dtype": "string"}, {"name": "context", "dtype": "string"}], "splits": [{"name": "train", "num_bytes": 385476, "num_examples": 240}, {"name": "validation", "num_bytes": 69252, "num_examples": 40}], "download_size": 213734, "dataset_size": 454728}} | 2023-11-30T07:03:41+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "find_first_sent_train_100_eval_40_recite"
More Information needed | [
"# Dataset Card for \"find_first_sent_train_100_eval_40_recite\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"find_first_sent_train_100_eval_40_recite\"\n\nMore Information needed"
] | [
6,
29
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"find_first_sent_train_100_eval_40_recite\"\n\nMore Information needed"
] |
a7f00fdd33aaaa072d50380c5e4419b5260095ea | # Dataset Card for "find_second_sent_train_100_eval_40_recite"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | tyzhu/find_second_sent_train_100_eval_40_recite | [
"region:us"
] | 2023-11-30T07:03:59+00:00 | {"configs": [{"config_name": "default", "data_files": [{"split": "train", "path": "data/train-*"}, {"split": "validation", "path": "data/validation-*"}]}], "dataset_info": {"features": [{"name": "inputs", "dtype": "string"}, {"name": "targets", "dtype": "string"}, {"name": "title", "dtype": "string"}, {"name": "context", "dtype": "string"}], "splits": [{"name": "train", "num_bytes": 384059, "num_examples": 240}, {"name": "validation", "num_bytes": 68179, "num_examples": 40}], "download_size": 212699, "dataset_size": 452238}} | 2023-11-30T07:04:10+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "find_second_sent_train_100_eval_40_recite"
More Information needed | [
"# Dataset Card for \"find_second_sent_train_100_eval_40_recite\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"find_second_sent_train_100_eval_40_recite\"\n\nMore Information needed"
] | [
6,
28
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"find_second_sent_train_100_eval_40_recite\"\n\nMore Information needed"
] |
27ca2b894b802b91b088112bb190c6cffecc6960 | # Dataset Card for "find_last_sent_train_100_eval_40_recite"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | tyzhu/find_last_sent_train_100_eval_40_recite | [
"region:us"
] | 2023-11-30T07:04:27+00:00 | {"configs": [{"config_name": "default", "data_files": [{"split": "train", "path": "data/train-*"}, {"split": "validation", "path": "data/validation-*"}]}], "dataset_info": {"features": [{"name": "inputs", "dtype": "string"}, {"name": "targets", "dtype": "string"}, {"name": "title", "dtype": "string"}, {"name": "context", "dtype": "string"}], "splits": [{"name": "train", "num_bytes": 384450, "num_examples": 240}, {"name": "validation", "num_bytes": 69066, "num_examples": 40}], "download_size": 214121, "dataset_size": 453516}} | 2023-11-30T07:04:36+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "find_last_sent_train_100_eval_40_recite"
More Information needed | [
"# Dataset Card for \"find_last_sent_train_100_eval_40_recite\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"find_last_sent_train_100_eval_40_recite\"\n\nMore Information needed"
] | [
6,
28
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"find_last_sent_train_100_eval_40_recite\"\n\nMore Information needed"
] |
7db9399874d25f1e7572c4905c28628f1fe52dca | # Dataset Card for "find_first_sent_train_200_eval_40_recite"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | tyzhu/find_first_sent_train_200_eval_40_recite | [
"region:us"
] | 2023-11-30T07:04:53+00:00 | {"configs": [{"config_name": "default", "data_files": [{"split": "train", "path": "data/train-*"}, {"split": "validation", "path": "data/validation-*"}]}], "dataset_info": {"features": [{"name": "inputs", "dtype": "string"}, {"name": "targets", "dtype": "string"}, {"name": "title", "dtype": "string"}, {"name": "context", "dtype": "string"}], "splits": [{"name": "train", "num_bytes": 720201, "num_examples": 440}, {"name": "validation", "num_bytes": 71058, "num_examples": 40}], "download_size": 326588, "dataset_size": 791259}} | 2023-11-30T07:05:01+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "find_first_sent_train_200_eval_40_recite"
More Information needed | [
"# Dataset Card for \"find_first_sent_train_200_eval_40_recite\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"find_first_sent_train_200_eval_40_recite\"\n\nMore Information needed"
] | [
6,
29
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"find_first_sent_train_200_eval_40_recite\"\n\nMore Information needed"
] |
78e44177b0a6e38702643f2a7a56bc32f1132992 | # Dataset Card for "find_second_sent_train_200_eval_40_recite"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | tyzhu/find_second_sent_train_200_eval_40_recite | [
"region:us"
] | 2023-11-30T07:05:19+00:00 | {"configs": [{"config_name": "default", "data_files": [{"split": "train", "path": "data/train-*"}, {"split": "validation", "path": "data/validation-*"}]}], "dataset_info": {"features": [{"name": "inputs", "dtype": "string"}, {"name": "targets", "dtype": "string"}, {"name": "title", "dtype": "string"}, {"name": "context", "dtype": "string"}], "splits": [{"name": "train", "num_bytes": 719759, "num_examples": 440}, {"name": "validation", "num_bytes": 71562, "num_examples": 40}], "download_size": 326351, "dataset_size": 791321}} | 2023-11-30T07:05:26+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "find_second_sent_train_200_eval_40_recite"
More Information needed | [
"# Dataset Card for \"find_second_sent_train_200_eval_40_recite\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"find_second_sent_train_200_eval_40_recite\"\n\nMore Information needed"
] | [
6,
28
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"find_second_sent_train_200_eval_40_recite\"\n\nMore Information needed"
] |
f6e03c88e7652bb9814382b26f514a16cc015798 | # Dataset Card for "find_last_sent_train_200_eval_40_recite"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | tyzhu/find_last_sent_train_200_eval_40_recite | [
"region:us"
] | 2023-11-30T07:05:43+00:00 | {"configs": [{"config_name": "default", "data_files": [{"split": "train", "path": "data/train-*"}, {"split": "validation", "path": "data/validation-*"}]}], "dataset_info": {"features": [{"name": "inputs", "dtype": "string"}, {"name": "targets", "dtype": "string"}, {"name": "title", "dtype": "string"}, {"name": "context", "dtype": "string"}], "splits": [{"name": "train", "num_bytes": 719798, "num_examples": 440}, {"name": "validation", "num_bytes": 70410, "num_examples": 40}], "download_size": 326541, "dataset_size": 790208}} | 2023-11-30T07:05:49+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "find_last_sent_train_200_eval_40_recite"
More Information needed | [
"# Dataset Card for \"find_last_sent_train_200_eval_40_recite\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"find_last_sent_train_200_eval_40_recite\"\n\nMore Information needed"
] | [
6,
28
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"find_last_sent_train_200_eval_40_recite\"\n\nMore Information needed"
] |
7f6370978946751687462a29494830d3d697d38f | # Dataset Card for "find_first_sent_train_400_eval_40_recite"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | tyzhu/find_first_sent_train_400_eval_40_recite | [
"region:us"
] | 2023-11-30T07:06:05+00:00 | {"configs": [{"config_name": "default", "data_files": [{"split": "train", "path": "data/train-*"}, {"split": "validation", "path": "data/validation-*"}]}], "dataset_info": {"features": [{"name": "inputs", "dtype": "string"}, {"name": "targets", "dtype": "string"}, {"name": "title", "dtype": "string"}, {"name": "context", "dtype": "string"}], "splits": [{"name": "train", "num_bytes": 1368863, "num_examples": 840}, {"name": "validation", "num_bytes": 71989, "num_examples": 40}], "download_size": 536857, "dataset_size": 1440852}} | 2023-11-30T07:06:13+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "find_first_sent_train_400_eval_40_recite"
More Information needed | [
"# Dataset Card for \"find_first_sent_train_400_eval_40_recite\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"find_first_sent_train_400_eval_40_recite\"\n\nMore Information needed"
] | [
6,
29
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"find_first_sent_train_400_eval_40_recite\"\n\nMore Information needed"
] |
8b8a23d1fac54c8f7389be2b1f75cb97bda2d37b | # Dataset Card for "find_second_sent_train_400_eval_40_recite"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | tyzhu/find_second_sent_train_400_eval_40_recite | [
"region:us"
] | 2023-11-30T07:06:30+00:00 | {"configs": [{"config_name": "default", "data_files": [{"split": "train", "path": "data/train-*"}, {"split": "validation", "path": "data/validation-*"}]}], "dataset_info": {"features": [{"name": "inputs", "dtype": "string"}, {"name": "targets", "dtype": "string"}, {"name": "title", "dtype": "string"}, {"name": "context", "dtype": "string"}], "splits": [{"name": "train", "num_bytes": 1369335, "num_examples": 840}, {"name": "validation", "num_bytes": 71727, "num_examples": 40}], "download_size": 536461, "dataset_size": 1441062}} | 2023-11-30T07:06:37+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "find_second_sent_train_400_eval_40_recite"
More Information needed | [
"# Dataset Card for \"find_second_sent_train_400_eval_40_recite\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"find_second_sent_train_400_eval_40_recite\"\n\nMore Information needed"
] | [
6,
28
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"find_second_sent_train_400_eval_40_recite\"\n\nMore Information needed"
] |
c3a59fa9fa51dc55bf7327d267aa26a58adb9965 | # Dataset Card for "find_last_sent_train_400_eval_40_recite"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | tyzhu/find_last_sent_train_400_eval_40_recite | [
"region:us"
] | 2023-11-30T07:06:53+00:00 | {"configs": [{"config_name": "default", "data_files": [{"split": "train", "path": "data/train-*"}, {"split": "validation", "path": "data/validation-*"}]}], "dataset_info": {"features": [{"name": "inputs", "dtype": "string"}, {"name": "targets", "dtype": "string"}, {"name": "title", "dtype": "string"}, {"name": "context", "dtype": "string"}], "splits": [{"name": "train", "num_bytes": 1367220, "num_examples": 840}, {"name": "validation", "num_bytes": 72022, "num_examples": 40}], "download_size": 536123, "dataset_size": 1439242}} | 2023-11-30T07:07:02+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "find_last_sent_train_400_eval_40_recite"
More Information needed | [
"# Dataset Card for \"find_last_sent_train_400_eval_40_recite\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"find_last_sent_train_400_eval_40_recite\"\n\nMore Information needed"
] | [
6,
28
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"find_last_sent_train_400_eval_40_recite\"\n\nMore Information needed"
] |
d8cfb83baf676a91284d1d6e4772257a0abcaa08 | # Dataset Card for "ruTextNorm-data"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | 0x7o/ruTextNorm-data | [
"region:us"
] | 2023-11-30T07:18:37+00:00 | {"dataset_info": {"features": [{"name": "full", "dtype": "string"}, {"name": "short", "dtype": "string"}], "splits": [{"name": "train", "num_bytes": 245430258, "num_examples": 761435}], "download_size": 135847160, "dataset_size": 245430258}} | 2023-11-30T07:20:16+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "ruTextNorm-data"
More Information needed | [
"# Dataset Card for \"ruTextNorm-data\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"ruTextNorm-data\"\n\nMore Information needed"
] | [
6,
16
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"ruTextNorm-data\"\n\nMore Information needed"
] |
d30aa238fd8a4a6a3788abe4386bc462a4e0a066 | # PSegs iOS Lidar Extension
[](https://opensource.org/licenses/Apache-2.0)
This project contains data captured using Lidar-equipped iPhone(s)
for use as an extension with the
[PSegs](https://github.com/pwais/psegs) project.
# Structure
* [threeDScannerApp_data](https://huggingface.co/datasets/PSegs/psegs-ios-lidar-ext/tree/main/threeDScannerApp_data) - This is test data captured
using the [3D Scanner App](https://3dscannerapp.com/) for iOS.
* [ps_external_test_fixtures](https://huggingface.co/datasets/PSegs/psegs-ios-lidar-ext/tree/main/ps_external_test_fixtures) - These are fixtures
created using the data in this repo and code in
[PSegs](https://github.com/pwais/psegs). They are hosted here and
provided to power [PSegs](https://github.com/pwais/psegs) unit tests. | PSegs/psegs-ios-lidar-ext | [
"size_categories:n<1K",
"license:apache-2.0",
"region:us"
] | 2023-11-30T07:49:55+00:00 | {"license": "apache-2.0", "size_categories": ["n<1K"]} | 2023-11-30T08:04:32+00:00 | [] | [] | TAGS
#size_categories-n<1K #license-apache-2.0 #region-us
| # PSegs iOS Lidar Extension
for use as an extension with the
PSegs project.
# Structure
* threeDScannerApp_data - This is test data captured
using the 3D Scanner App for iOS.
* ps_external_test_fixtures - These are fixtures
created using the data in this repo and code in
PSegs. They are hosted here and
provided to power PSegs unit tests. | [
"# PSegs iOS Lidar Extension\n\n\nfor use as an extension with the \nPSegs project.",
"# Structure\n * threeDScannerApp_data - This is test data captured\n using the 3D Scanner App for iOS.\n * ps_external_test_fixtures - These are fixtures\n created using the data in this repo and code in \n\t PSegs. They are hosted here and \n\t provided to power PSegs unit tests."
] | [
"TAGS\n#size_categories-n<1K #license-apache-2.0 #region-us \n",
"# PSegs iOS Lidar Extension\n\n\nfor use as an extension with the \nPSegs project.",
"# Structure\n * threeDScannerApp_data - This is test data captured\n using the 3D Scanner App for iOS.\n * ps_external_test_fixtures - These are fixtures\n created using the data in this repo and code in \n\t PSegs. They are hosted here and \n\t provided to power PSegs unit tests."
] | [
24,
48,
74
] | [
"passage: TAGS\n#size_categories-n<1K #license-apache-2.0 #region-us \n# PSegs iOS Lidar Extension\n\n\nfor use as an extension with the \nPSegs project.# Structure\n * threeDScannerApp_data - This is test data captured\n using the 3D Scanner App for iOS.\n * ps_external_test_fixtures - These are fixtures\n created using the data in this repo and code in \n\t PSegs. They are hosted here and \n\t provided to power PSegs unit tests."
] |
88ba1e2d0ad8f2b2d7cf2bff6b6f2ca50f832c97 | # Long SlimPajama
This dataset contains filtered documents that are longer thhan 8000 tokens.
We also provide the processing script for filtering and tokenization.
To filter the dataset, run:
```bash
python get_long_text_data.py \
--data_path SlimPajama-627B/train/chunk1 \
--output_name long_text_data_train_chunk1.jsonl \
--word_limit 8000 \
--num_cpus 64
```
To tokenize data, run the following:
```
python tokenize_data.py \
--tokenizer "meta-llama/Llama-2-7b-hf" \
--input_file long_text_data_train_chunk1.jsonl \
--output_path llama
``` | qywu/slimpajama_long | [
"region:us"
] | 2023-11-30T08:04:44+00:00 | {} | 2023-11-30T09:06:23+00:00 | [] | [] | TAGS
#region-us
| # Long SlimPajama
This dataset contains filtered documents that are longer thhan 8000 tokens.
We also provide the processing script for filtering and tokenization.
To filter the dataset, run:
To tokenize data, run the following:
| [
"# Long SlimPajama\n\nThis dataset contains filtered documents that are longer thhan 8000 tokens.\nWe also provide the processing script for filtering and tokenization.\n\nTo filter the dataset, run:\n\n\nTo tokenize data, run the following:"
] | [
"TAGS\n#region-us \n",
"# Long SlimPajama\n\nThis dataset contains filtered documents that are longer thhan 8000 tokens.\nWe also provide the processing script for filtering and tokenization.\n\nTo filter the dataset, run:\n\n\nTo tokenize data, run the following:"
] | [
6,
55
] | [
"passage: TAGS\n#region-us \n# Long SlimPajama\n\nThis dataset contains filtered documents that are longer thhan 8000 tokens.\nWe also provide the processing script for filtering and tokenization.\n\nTo filter the dataset, run:\n\n\nTo tokenize data, run the following:"
] |
35a1265ca8652e32e76369ade380df0ddb29cc08 | # Dataset Card for "102flowers_caption"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | cherry0324/102flowers_caption | [
"region:us"
] | 2023-11-30T08:07:04+00:00 | {"dataset_info": {"features": [{"name": "image", "dtype": "image"}, {"name": "text", "dtype": "string"}], "splits": [{"name": "train", "num_bytes": 270132296.848, "num_examples": 6552}], "download_size": 277230828, "dataset_size": 270132296.848}, "configs": [{"config_name": "default", "data_files": [{"split": "train", "path": "data/train-*"}]}]} | 2023-11-30T08:24:19+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "102flowers_caption"
More Information needed | [
"# Dataset Card for \"102flowers_caption\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"102flowers_caption\"\n\nMore Information needed"
] | [
6,
16
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"102flowers_caption\"\n\nMore Information needed"
] |
cd2ac81f7584d4ec33631192be439a1dded3001d |
원본 데이터셋: [GAIR/lima](https://huggingface.co/datasets/GAIR/lima) | nlp-with-deeplearning/ko.lima | [
"size_categories:1K<n<10K",
"language:en",
"language:ko",
"license:cc-by-nc-sa-4.0",
"region:us"
] | 2023-11-30T08:24:22+00:00 | {"language": ["en", "ko"], "license": "cc-by-nc-sa-4.0", "size_categories": ["1K<n<10K"]} | 2023-12-04T03:31:00+00:00 | [] | [
"en",
"ko"
] | TAGS
#size_categories-1K<n<10K #language-English #language-Korean #license-cc-by-nc-sa-4.0 #region-us
|
원본 데이터셋: GAIR/lima | [] | [
"TAGS\n#size_categories-1K<n<10K #language-English #language-Korean #license-cc-by-nc-sa-4.0 #region-us \n"
] | [
40
] | [
"passage: TAGS\n#size_categories-1K<n<10K #language-English #language-Korean #license-cc-by-nc-sa-4.0 #region-us \n"
] |
4e9edfa727f800b6f595bc2ee7420527156562b2 | The CICIDS2017 dataset consists of labeled network flows, including full packet payloads in pcap format, the corresponding profiles and the labeled flows (GeneratedLabelledFlows.zip) and CSV files for machine and deep learning purpose (MachineLearningCSV.zip) are publicly available for researchers. If you are using our dataset, you should cite our related paper which outlining the details of the dataset and its underlying principles:
* Iman Sharafaldin, Arash Habibi Lashkari, and Ali A. Ghorbani, “Toward Generating a New Intrusion Detection Dataset and Intrusion Traffic Characterization”, 4th International Conference on Information Systems Security and Privacy (ICISSP), Portugal, January 2018 | c01dsnap/CIC-IDS2017 | [
"license:other",
"region:us"
] | 2023-11-30T08:43:09+00:00 | {"license": "other", "license_name": "other", "license_link": "LICENSE"} | 2023-11-30T09:21:34+00:00 | [] | [] | TAGS
#license-other #region-us
| The CICIDS2017 dataset consists of labeled network flows, including full packet payloads in pcap format, the corresponding profiles and the labeled flows (URL) and CSV files for machine and deep learning purpose (URL) are publicly available for researchers. If you are using our dataset, you should cite our related paper which outlining the details of the dataset and its underlying principles:
* Iman Sharafaldin, Arash Habibi Lashkari, and Ali A. Ghorbani, “Toward Generating a New Intrusion Detection Dataset and Intrusion Traffic Characterization”, 4th International Conference on Information Systems Security and Privacy (ICISSP), Portugal, January 2018 | [] | [
"TAGS\n#license-other #region-us \n"
] | [
11
] | [
"passage: TAGS\n#license-other #region-us \n"
] |
033dfacd4b23e4171dd40e2001ecdac1eba9a748 | # 🚢 Korean Stanford Human Preferences Dataset (Ko.SHP)
이 데이터셋은 자체 구축한 번역기를 활용하여 [stanfordnlp/SHP](https://huggingface.co/datasets/stanfordnlp/SHP) 데이터셋을 번역한 것입니다.
아래의 내용은 해당 번역기로 README 파일을 번역한 것입니다. 참고 부탁드립니다.
**If you mention this dataset in a paper, please cite the paper:** [Understanding Dataset Difficulty with V-Usable Information (ICML 2022)](https://proceedings.mlr.press/v162/ethayarajh22a.html).
## Summary
SHP는 요리에서 법률 조언에 이르기까지 18가지 다른 주제 영역의 질문/지침에 대한 응답에 대한 **385K 집단 인간 선호도** 데이터 세트이다.
기본 설정은 다른 응답에 대 한 한 응답의 유용성을 반영 하기 위한 것이며 RLHF 보상 모델 및 NLG 평가 모델 (예: [SteamSHP](https://huggingface.co/stanfordnlp/SteamSHP-flan-t5-xl))을 훈련 하는 데 사용 하도록 설정 됩니다.
각각의 예는 질문/지시 및 그 게시물에 대한 한 쌍의 최상위 코멘트를 갖는 레딧 게시물이며, 여기서 하나의 코멘트는 (종합적으로) 레딧 사용자에 의해 더 선호된다.
SHP는 댓글 A가 댓글 B 뒤에 작성되었지만 그럼에도 불구하고 점수가 더 높으면 표면적으로는 A가 B보다 더 선호된다는 사실을 이용한다.
A가 B보다 먼저 작성되었으면 더 높은 점수가 더 많은 가시성의 결과일 수 있기 때문에 결론을 내릴 수 없었다.
우리는 선호도 라벨이 어떤 반응이 덜 *유해*하기보다는 더 *도움이* 되는지를 반영하기 위한 데이터를 선택했으며 후자는 많은 과거 작업의 초점이다.
SHP는 [Anthropic의 HH-RLHF 데이터 세트](https://huggingface.co/datasets/Anthropic/hh-rlhf)와 어떻게 다른가요?
특히, SHP의 모든 데이터는 자연적으로 발생하고 인간이 작성하는 반면 HH-RLHF의 응답은 기계 작성되어 서로를 보완할 수 있는 두 가지 매우 다른 분포를 제공한다.
| Dataset | Size | Input | Label | Domains | Data Format | Length |
| -------------------- | ---- | -------------------------- | ---------------------------- | ------------------------- | ------------------------------------- | --------------- |
| SHP | 385K | 자연 발생 인간 작성 응답 | Collective Human Preference | 18 (labelled) | Question/Instruction + Response (Single-turn) | 최대 10.1K T5 토큰 |
| HH-RLHF | 91K | LLM과의 대화 | 개별 인간 선호도 | 레이블이 지정되지 않음 | Live Chat (Multi-turn) | 최대 1.5K T5 토큰 |
SHP는 [ELI5](https://huggingface.co/datasets/eli5#source-data)와 같이 Reddit을 스크래핑한 다른 데이터 세트와 어떻게 다른가요?
SHP는 타임스탬프 정보를 사용 하 여 선호도를 유추 하는 반면 ELI5는 주석 및 점수만 제공 합니다. 후자는 이전에 만든 주석이 더 많은 가시성에서 더 높은 점수를 얻는 경향이 있기 때문에 선호도를 유추 하기에 충분하지 않습니다.
또한 더 많은 도메인의 데이터를 포함합니다.
| Dataset | Size | Comments + Scores | Preferences | Number of Domains |
| -------------------- | ---- | ------------------ | -------------| ------------------ |
| SHP | 385K | Yes | Yes | 18 |
| ELI5 | 270K | Yes | No | 3 |
## 데이터 구조
각 하위 레딧에 대해 하나씩 18개의 디렉터리가 있으며 각 디렉터리에는 학습, 유효성 검사 및 테스트 데이터를 위한 JSONL 파일이 포함되어 있습니다.
Huggingface의 `datasets` 라이브러리를 사용하여 데이터를 가져오는 방법은 다음과 같습니다.
```python
from datasets import load_dataset
# Load all the data
dataset = load_dataset("stanfordnlp/shp")
# Load one of the subreddits
dataset = load_dataset("stanfordnlp/shp", data_dir="askculinary")
```
다음은 `askculinary/train.json`의 예입니다.
```
{
`post_id`:"qt3nxl",
`domain`:"askculinary_train",
`upvote_ratio`:0.98,
`history`:"라즈베리를 분해하는 가장 좋은 방법은 무엇입니까? 이와 같이, 그러나 개별 씨앗까지: https:\/\/i.imgur.com\/Z0c6ZKE.jpg 핀셋으로 분리해 왔는데 시간이 많이 걸립니다. 이번 주말까지 약 10파운드가 소요됩니다.
`c_root_id_A`:"hkh25sc",
`c_root_id_B`:"hkh25lp",
`created_at_utc_A`:1636822112,
`created_at_utc_B`:1636822110,
`score_A`:340,
`score_B`:166,
`human_ref_A`:"Pectinex, 아마도? 셀룰로오스를 분해하는 효소입니다. citrus를 사용하면 pectinex의 묽은 용액에 밤새 앉아 결합 조직을 분해하게 됩니다. 결국 완벽한 citrus supremes가 됩니다. 라즈베리를 더 짧은 시간 동안 앉게 되면 같은 방식으로 종자를 분리할 수 있는지 궁금합니다. 여기 예제가 있습니다. https:\/\/www.chefsteps.com\/activities\/perfect-citrus-supreme",
`human_ref_B`:"라즈베리 주스는 처음에는 밝은 얼룩을 만들지만 몇 주 후면 거의 아무것도 사라지기 시작합니다. 천연 염료 세계에서 탈주 염료로 알려진 것은 세탁이나 빛에 노출되지 않아도 사라질 것입니다. 그녀가 드레스에 이 얼룩의 멋진 사진을 많이 얻기를 바랍니다. 곧 그것이 그녀가 남긴 전부이기 때문입니다."
`labels`:1,
`seconds_difference`:2.0,
`score_ratio`:2.0481927711
}
```
상기 필드들은:
- ```post_id```: the ID of the Reddit post (string)
- ```domain```: subreddit and split the example is drawn from, separated by underscore (string)
- ```upvote_ratio```: 긍정 (일명 upvotes) (float) 게시물에서 받은 투표 비율입니다.
- ```history```: Post title concatented to post body (string)
- ```c_root_id_A```: comment A의 ID (string)
- ```c_root_id_B```: comment B (string)의 ID
- ```created_at_utc_A```: utc timestamp of when comment A is created (integer)
- ```created_at_utc_B```: utc timestamp of when comment B is created (integer)
- ```score_A```: (# positive votes - # negative votes + 1) received by comment A (integer)
- ```score_B```: (# positive votes - # negative votes + 1) received by comment B (integer)
- ```human_ref_A```: comment A의 텍스트 (string)
- ```human_ref_B```: comment B의 텍스트 (string)
- ```labels```: 선호도 레이블 -- A가 B보다 선호되는 경우 1이고, B가 A보다 선호되는 경우 0입니다. 레이블 분포가 대략 50/50이 되도록 무작위화되었습니다. (정수)
- ```seconds_difference```: 덜 선호되는 코멘트가 생성된 후 몇 초 후에 더 선호되는 코멘트가 생성되었는지(항상 >= 0일 것임) (정수)
- ```score_ratio```: 더 선호하는 댓글의 점수와 덜 선호하는 댓글의 점수의 비율 (>= 1) (float)
## Dataset Design
### 도메인 선택
데이터는 *서브레딧* 이라는 토픽별 포라로 구성된 공개 포럼인 Reddit에서 공급됩니다.
예를 들어 `askculinary` 하위 레딧은 사용자가 요리 관련 질문을 하고 다른 사용자에 의해 응답 되는 것입니다.
SHP에는 18개의 다른 하위 레딧에서 긁어낸 주석에 대한 열차, 유효성 검사 및 테스트 분할이 포함되어 있습니다. 우리는 다음을 기반으로 하위 레딧을 선택했습니다.
1. 잘 알려진 것인지 여부(가입자수 >= 100K)
2. 게시물이 질문 또는 지시를 내릴 것으로 예상되었는지 여부
3. 응답이 얼마나 *도움이* 되는지에 따라 평가되는지 여부
4. 코멘트가 전적으로 개인 경험에 대한 것이 아니라 일부 객관성에 뿌리를 두어야 하는지 여부(예: `askscience` 대 `AskAmericans`)입니다.
열차/검증/테스트 분할은 하위 레딧의 포스트 ID를 각각 90%/5%/5% 비율로 분할하여 생성되어 여러 분할에 포스트가 나타나지 않는다.
상이한 게시물들은 상이한 수의 코멘트들을 갖기 때문에, 각각의 분할에서의 선호들의 수는 정확히 90%/5%/5%가 아니다:
| subreddit | train | validation | test | total |
| ------------------ | -------: | ---------: | ---: | ----: |
| askacademia | 31450 | 2095 | 1708 | 35253 |
| askanthropology | 3910 | 203 | 268 | 4381 |
| askbaking | 44007 | 2096 | 1544 | 47647 |
| askcarguys | 3227 | 159 | 117 | 3503 |
| askculinary | 45710 | 2094 | 2563 | 50367 |
| askdocs | 6449 | 315 | 455 | 7219 |
| askengineers | 57096 | 3154 | 2638 | 62888 |
| askhistorians | 3264 | 113 | 164 | 3541 |
| askhr | 8295 | 641 | 395 | 9331 |
| askphilosophy | 10307 | 608 | 677 | 11592 |
| askphysics | 7364 | 409 | 587 | 8360 |
| askscience | 13316 | 899 | 977 | 15192 |
| asksciencefiction | 29382 | 1576 | 1987 | 32945 |
| asksocialscience | 2706 | 147 | 188 | 3041 |
| askvet | 3300 | 170 | 224 | 3694 |
| changemyview | 38173 | 1637 | 1836 | 41646 |
| explainlikeimfive | 19592 | 1014 | 1070 | 21676 |
| legaladvice | 21170 | 1106 | 1011 | 23287 |
| ALL | 348718 | 18436 | 18409 | 385563 |
### 데이터 선택
포스트/댓글의 점수는 1에 사용자로부터의 상향 투표 수(승인)를 곱하고 하향 투표 수(승인 취소)를 뺀 값입니다.
점수의 값은 상대적입니다. 트래픽이 많은 하위 레딧(게시물)에서는 점수가 높은 게시물(댓글)이 더 많습니다.
게시물에서 더 일찍 게시된 댓글은 단순히 노출이 많아 점수가 더 높은 경향이 있을 것이므로 선호도를 추론할 때 타임스탬프 정보를 사용하는 것이 필수적이다.
게시물 P와 두 개의 주석(A,B)이 주어지면 데이터 세트에 선호도 A > B만 포함했다.
1. A는 *늦지 않게* B로 작성되었고 A는 B보다 높은 점수를 갖는다.
2. 게시물은 2023년 이전에 만들어진 셀프-포스트(즉, 텍스트의 본문이고 다른 페이지로의 링크가 아님)이며, 편집되지 않았으며, NSFW(18 초과)가 아니다.
3. 삭제된 사용자, 사회자 또는 게시물 작성자에 의해 어떠한 코멘트도 이루어지지 않았다. 게시물은 삭제된 사용자 또는 진행자가 만들지 않았습니다.
4. 게시물은 점수가 >=10이고 각 코멘트는 점수가 >=2(적어도 한 번 이상 투표)이다.
주석이 있는 게시물은 `n` 데이터에서 최대 (`n` `2`) 환경 설정을 선택할 수 있습니다.
게시물당 댓글 수는 파레토 배포이기 때문에 상대적으로 적은 수의 게시물이 데이터를 지배하는 것을 방지하기 위해 게시물당 50개의 댓글으로 스크래핑을 제한했다.
이는 위의 모든 기준을 충족해야 하기 때문에 실제로는 훨씬 적은 수이지만 각 게시물에 데이터 집합에서 최대 (`50` `2`를 선택) 주석이 있을 수 있음을 의미 합니다.
레드딧은 서브레드딧마다 상위 1000개 이상의 게시물을 얻는 것을 매우 어렵게 만든다.
최상위 1,000개의 게시물부터 시작하여 Reddit의 검색 기능을 사용하여 각 게시물과 가장 유사한 25개의 게시물을 검색하여 하위 레딧당 최대 7500개의 고유한 게시물 ID를 얻었다.
### 전처리
전처리를 최소한으로 유지하려고 노력했습니다. 서브레디트-특정 약어는 확장되었다(예를 들어, "CMV"를 "내 견해를 변경"으로).
하이퍼링크에서, 참조 텍스트만이 유지되고 URL이 제거되었다(URL이 기입된 경우, 그것은 유지되었다).
## 기본 설정 모델 만들기
### Finetuning
인간 선호도(예를 들어, NLG 평가 또는 RLHF 보상 모델에 대해)를 예측하기 위해 모델을 피니튜닝하고자 하는 경우, 여기 몇 가지 유용한 팁이 있다:
1. **데이터를 전처리합니다.* * 총 입력 길이는 모델의 토큰 제한 (일반적으로 512 토큰)에 적합 해야 합니다.
FLAN-T5와 같은 모델은 위치 임베딩을 사용하지만 512개 토큰 이상의 입력에서 손실을 조정하면 손실이 수렴하지 않는다는 것을 발견했다.
이를 방지 하려면 게시글 텍스트 (`history` 필드에서)를 가능한 한 잘라서 전체 입력이 512 토큰 아래에 있도록 합니다 (그러나 주석을 잘리지 않음).
여전히 512 토큰 이상이면 예제를 건너뜁니다.
2. **충분히 큰 모델을 사용** 합니다.
모든 트레이닝 데이터에 걸쳐 단일 FLAN-T5-xl 모델을 피니튜닝하는 것은 72-73%(전체 입력이 토큰 한계 내에 맞는 예시의 모든 도메인에 걸쳐) 사이의 테스트 정확도를 제공해야 하며, 개별 서브레딧의 경우 65-80% 범위이다.
3. **도메인 내 예측을 수행 합니다.* * 하위 레딧이 관련이 없는 경우 도메인 외 성능이 좋지 않습니다 (예: 환경 설정을 미세 조정 하 고 환경 설정을 테스트 하는 경우 `askculinary` `askcarguys`).
4. **더 적은 에폭에 대해 훈련** InstructGPT 종이 페이퍼는 1 에폭에 대해서만 보상 모델을 훈련하는 것을 제안합니다.
동일한 코멘트가 여러 선호도에서 나타나기 때문에 데이터에 과적합되기 쉽다.
5. **더 적은 데이터에 대한 교육이 도움이 될 수 있습니다* *.
큰 `score_ratio`를 사용하는 환경 설정(예: 주석 B의 점수가 2배인 주석 A)은 모델을 조정하기 위한 더 강력한 신호를 제공하므로 특정 이상의 환경 설정만 고려하려는 것일 수 있습니다 `score_ratio`.
게시물당 선호도 수는 Pareto-distributed이므로 모델이 특정 게시물에 과도하게 적합 하는 것을 방지 하기 위해 특정 게시물에서 선호도 수를 제한 하는 것이 좋습니다.
### 평가
약한 기본 설정보다 강력한 기본 설정을 예측하는 것이 더 쉽기 때문에 단일 정확도 값을 보고하는 대신 성능 곡선을 `score_ratio`의 함수로 보고하는 것이 좋습니다.
예를 들어, 여기 위의 제안들을 사용하여 질문적 데이터에 대해 트레이닝된 FLAN-T5-xl 모델에 대한 정확도 곡선이 있다.
주황색 라인은 2+ 스코어 비율을 갖는 선호도에만 피니튜닝하고 과적합을 방지하기 위해 각 포스트로부터 5개 이하의 선호도를 사용하는 것이다:
로 이루어진 군에서 선택되는 어느 하나인 것을 특징으로 하는 유기 발광 표시 장치. [그래프](curve.png)
우리는 더 낮지만 더 높은 품질의 데이터를 미세 조정하는 것이 실제 단점이 없는 점수 비율이 3.5 미만인 테스트 데이터에 대한 더 높은 정확도로 이어진다는 것을 알 수 있다!
토큰 제한 내에 입력이 맞지 않는 예는 모델에서 처리할 것으로 예상할 수 없기 때문에 실험에서 제외되었다.
### SteamSHP - Open-Source Preference Model
우리는 SHP 데이터 세트와 Anthropic의 HH-RLHF의 도움 데이터 모두에 대해 두 개의 FLAN-T5 모델을 미세 조정했다. 그들은
- 테스트 데이터에서 72.8%를 달성하는 3B 매개 변수 모델인 [SteamSHP-XL](https://huggingface.co/stanfordnlp/SteamSHP-flan-t5-xl)입니다.
- 테스트 데이터에서 72.0%를 달성하는 780M 매개 변수 모델인 [SteamSHP-Large](https://huggingface.co/stanfordnlp/SteamSHP-flan-t5-large)입니다.
NLG 평가, RLHF에 대한 보상 모델 구축 또는 적합하다고 생각하는 다른 목적으로 스팀SHP를 사용하는 것이 좋습니다!
## 편향 및 제한 사항
### Biases
NSFW(18세 이상) 콘텐츠로 게시물을 걸러내고, 잘 조정되고 괴롭힘과 편협에 대한 정책이 있는 하위 레딧을 선택했지만 일부 데이터에는 차별적이거나 해로운 언어가 포함될 수 있다.
데이터는 데이터 세트 작성자의 보기를 반영하지 않습니다.
이러한 하위 레딧의 레딧 사용자도 광범위한 모집단을 대표하지 않는다.
하위 레딧별 인구 통계 정보는 사용할 수 없지만 전체 레딧 사용자는 불균형적으로 남성이며 선진국, 서양 및 영어 사용 국가에서 왔습니다 ([Pew Research](https://www.pewresearch.org/internet/2013/07/03/6-of-online-adults-are-reddit-users/)).
이 데이터에 대해 학습된 모델을 사용하기 전에 이 점을 염두에 두십시오.
### 제한 사항
SHP의 선호도 레이블은 지시/질문이 주어졌을 때 한 응답이 다른 응답과 얼마나 *도움이* 되는지 반영 하기 위한 것입니다.
SHP는 좋은 독성 검출기를 배우는 데 필요한 독성 함량을 포함하도록 설계되지 않았기 때문에 위해 최소화에서 사용하기 위한 것이 아니다.
환경 설정 레이블이 더 적은 해를 나타내는 데이터를 찾는 경우 [Anthropic의 HH-RLHF](https://huggingface.co/datasets/Anthropic/hh-rlhf)의 유해성 분할을 권장합니다.
또 다른 한계는 SHP에서 선호되는 응답이 반드시 더 사실적인 응답은 아니라는 것이다.
일부 논평은 그들의 반응을 정당화하기 위해 인용을 제공하지만 대부분은 그렇지 않다.
여기에는 `askhistorians` 하위 레딧과 같은 예외가 있으며, 이는 크게 조정되며 답변이 인용을 제공할 것으로 예상된다.
SHP의 집단 선호도 라벨은 가중치가 없는 합계를 취하기 전에 사용자에게 각 코멘트에 독립적으로 투표하도록 요청하면 반드시 얻을 수 있는 것은 아니다.
Reddit에 대한 주석 점수는 공개적이며 사용자 환경 설정에 영향을 미치는 것으로 알려져 있기 때문입니다. 높은 점수는 [(Muchnik et al., 2013)](https://pubmed.ncbi.nlm.nih.gov/23929980/)보다 긍정적인 표를 얻을 가능성을 높입니다.
이 "허딩 효과"가 사용자의 선호도를 일시적으로 또는 영구적으로 이동시키는지 여부는 불분명하다.
따라서, SHP가 집단적 인간 선호도를 반영하지만, SHP에 대해 훈련된 모델은 개별 선호도가 다르게 집계되는 설정으로 일반화되지 않을 수 있다(예를 들어, 사용자는 현재 코멘트 점수를 전혀 보지 않고 독립적으로 투표하고, 사용자는 부여 후 투표 등).
그렉 스토다드가 지적해줘서 고마워요
## License
Last updated: 03/01/2023
이 데이터 세트는 Reddit과 직접 통신 또는 서면 동의 없이 [Reddit API 사용 약관](https://docs.google.com/a/reddit.com/forms/d/e/1FAIpQLSezNdDNK1-P8mspSbmtC2r86Ee9ZRbC66u929cG2GX0T9UMyw/viewform)에 따라 Reddit을 스크래핑하여 만들었습니다.
사용 약관에 따라 "사용자 콘텐츠"는 Reddit이 아닌 사용자 자신이 소유하고 있으며 Reddit은 "사용자 콘텐츠를 복사 및 표시 하기 위해 독점적이지 않고 양도할 수 없으며 공개되지 않으며 취소할 수 있는 라이선스"를 부여 합니다.
Reddit을 스크래핑 하 여 만든 데이터 집합은 연구 커뮤니티에서 널리 사용 됩니다. 예를 들어 Facebook AI 리서치는 Reddit에서 스크래핑 된 데이터를 사용 하 여 라이선스 없이 사용 하도록 만든 2019년 [ELI5](https://huggingface.co/datasets/eli5#source-data) 데이터 집합을 만들었습니다.
인류성 AI는 다른 방법론을 사용 하 여 환경 설정에 대 한 [Reddit을 스크래핑](https://arxiv.org/pdf/2112.00861.pdf) 합니다. 그러나이 데이터는 공개 되지 않았습니다.
정기적인 일정에서 Reddit의 전체 덤프를 사용할 수 있도록 하는 [PushShift Reddit 데이터 세트](https://arxiv.org/abs/2001.08435)도 라이선스 없이 사용할 수 있습니다 (알고 있는 범위).
우리는 책임을 지지 않으며 이 데이터 세트의 다운스트림 사용을 명시적으로 또는 암시적으로 지지하지 않는다.
우리는 향후 어느 시점에서든 SHP 데이터 세트와 이 라이선스를 수정할 수 있는 권한을 보유합니다.
## Contact
데이터에 대한 질문이 있는 경우 [email protected]에 문의하십시오.
이 데이터 세트는 카윈 에타야라흐, 하이디(첸유) 장, 이중 왕 및 단 주라프스키에 의해 생성되었다.
## 인용
SHP는 다음 논문에서 제안한 기법을 이용하여 생성하였다. SHP 또는 스팀SHP 모델을 사용하는 경우 이 작업을 인용하십시오.
```
@InProceedings{pmlr-v162-ethayarajh22a,
title = {Understanding Dataset Difficulty with $\mathcal{V}$-Usable Information},
author = {Ethayarajh, Kawin and Choi, Yejin and Swayamdipta, Swabha},
booktitle = {Proceedings of the 39th International Conference on Machine Learning},
pages = {5988--6008},
year = {2022},
editor = {Chaudhuri, Kamalika and Jegelka, Stefanie and Song, Le and Szepesvari, Csaba and Niu, Gang and Sabato, Sivan},
volume = {162},
series = {Proceedings of Machine Learning Research},
month = {17--23 Jul},
publisher = {PMLR},
}
```
## 참조
Ethayarajh, K., Choi, Y. & Swayamdipta, S. (2022). Understanding Dataset Difficulty with $\mathcal{V}$-Usable Information. <i>Proceedings of the 39th International Conference on Machine Learning</i>, in <i>Proceedings of Machine Learning Research</i>. 162:5988-6008 Available from https://proceedings.mlr.press/v162/ethayarajh22a.html. | nlp-with-deeplearning/ko.SHP | [
"task_categories:text-generation",
"task_categories:question-answering",
"size_categories:100K<n<1M",
"language:ko",
"language:en",
"license:cc-by-nc-sa-4.0",
"human feedback",
"rlhf",
"preferences",
"reddit",
"preference model",
"RL",
"NLG",
"evaluation",
"arxiv:2112.00861",
"arxiv:2001.08435",
"region:us"
] | 2023-11-30T08:56:00+00:00 | {"language": ["ko", "en"], "license": "cc-by-nc-sa-4.0", "size_categories": ["100K<n<1M"], "task_categories": ["text-generation", "question-answering"], "tags": ["human feedback", "rlhf", "preferences", "reddit", "preference model", "RL", "NLG", "evaluation"]} | 2023-12-04T03:24:48+00:00 | [
"2112.00861",
"2001.08435"
] | [
"ko",
"en"
] | TAGS
#task_categories-text-generation #task_categories-question-answering #size_categories-100K<n<1M #language-Korean #language-English #license-cc-by-nc-sa-4.0 #human feedback #rlhf #preferences #reddit #preference model #RL #NLG #evaluation #arxiv-2112.00861 #arxiv-2001.08435 #region-us
| Korean Stanford Human Preferences Dataset (Ko.SHP)
==================================================
이 데이터셋은 자체 구축한 번역기를 활용하여 stanfordnlp/SHP 데이터셋을 번역한 것입니다.
아래의 내용은 해당 번역기로 README 파일을 번역한 것입니다. 참고 부탁드립니다.
If you mention this dataset in a paper, please cite the paper: Understanding Dataset Difficulty with V-Usable Information (ICML 2022).
Summary
-------
SHP는 요리에서 법률 조언에 이르기까지 18가지 다른 주제 영역의 질문/지침에 대한 응답에 대한 385K 집단 인간 선호도 데이터 세트이다.
기본 설정은 다른 응답에 대 한 한 응답의 유용성을 반영 하기 위한 것이며 RLHF 보상 모델 및 NLG 평가 모델 (예: SteamSHP)을 훈련 하는 데 사용 하도록 설정 됩니다.
각각의 예는 질문/지시 및 그 게시물에 대한 한 쌍의 최상위 코멘트를 갖는 레딧 게시물이며, 여기서 하나의 코멘트는 (종합적으로) 레딧 사용자에 의해 더 선호된다.
SHP는 댓글 A가 댓글 B 뒤에 작성되었지만 그럼에도 불구하고 점수가 더 높으면 표면적으로는 A가 B보다 더 선호된다는 사실을 이용한다.
A가 B보다 먼저 작성되었으면 더 높은 점수가 더 많은 가시성의 결과일 수 있기 때문에 결론을 내릴 수 없었다.
우리는 선호도 라벨이 어떤 반응이 덜 *유해*하기보다는 더 *도움이* 되는지를 반영하기 위한 데이터를 선택했으며 후자는 많은 과거 작업의 초점이다.
SHP는 Anthropic의 HH-RLHF 데이터 세트와 어떻게 다른가요?
특히, SHP의 모든 데이터는 자연적으로 발생하고 인간이 작성하는 반면 HH-RLHF의 응답은 기계 작성되어 서로를 보완할 수 있는 두 가지 매우 다른 분포를 제공한다.
SHP는 ELI5와 같이 Reddit을 스크래핑한 다른 데이터 세트와 어떻게 다른가요?
SHP는 타임스탬프 정보를 사용 하 여 선호도를 유추 하는 반면 ELI5는 주석 및 점수만 제공 합니다. 후자는 이전에 만든 주석이 더 많은 가시성에서 더 높은 점수를 얻는 경향이 있기 때문에 선호도를 유추 하기에 충분하지 않습니다.
또한 더 많은 도메인의 데이터를 포함합니다.
데이터 구조
------
각 하위 레딧에 대해 하나씩 18개의 디렉터리가 있으며 각 디렉터리에는 학습, 유효성 검사 및 테스트 데이터를 위한 JSONL 파일이 포함되어 있습니다.
Huggingface의 'datasets' 라이브러리를 사용하여 데이터를 가져오는 방법은 다음과 같습니다.
다음은 'askculinary/URL'의 예입니다.
상기 필드들은:
* : the ID of the Reddit post (string)
* : subreddit and split the example is drawn from, separated by underscore (string)
* : 긍정 (일명 upvotes) (float) 게시물에서 받은 투표 비율입니다.
* : Post title concatented to post body (string)
* : comment A의 ID (string)
* : comment B (string)의 ID
* : utc timestamp of when comment A is created (integer)
* : utc timestamp of when comment B is created (integer)
* : (# positive votes - # negative votes + 1) received by comment A (integer)
* : (# positive votes - # negative votes + 1) received by comment B (integer)
* : comment A의 텍스트 (string)
* : comment B의 텍스트 (string)
* : 선호도 레이블 -- A가 B보다 선호되는 경우 1이고, B가 A보다 선호되는 경우 0입니다. 레이블 분포가 대략 50/50이 되도록 무작위화되었습니다. (정수)
* : 덜 선호되는 코멘트가 생성된 후 몇 초 후에 더 선호되는 코멘트가 생성되었는지(항상 >= 0일 것임) (정수)
* : 더 선호하는 댓글의 점수와 덜 선호하는 댓글의 점수의 비율 (>= 1) (float)
Dataset Design
--------------
### 도메인 선택
데이터는 *서브레딧* 이라는 토픽별 포라로 구성된 공개 포럼인 Reddit에서 공급됩니다.
예를 들어 'askculinary' 하위 레딧은 사용자가 요리 관련 질문을 하고 다른 사용자에 의해 응답 되는 것입니다.
SHP에는 18개의 다른 하위 레딧에서 긁어낸 주석에 대한 열차, 유효성 검사 및 테스트 분할이 포함되어 있습니다. 우리는 다음을 기반으로 하위 레딧을 선택했습니다.
1. 잘 알려진 것인지 여부(가입자수 >= 100K)
2. 게시물이 질문 또는 지시를 내릴 것으로 예상되었는지 여부
3. 응답이 얼마나 *도움이* 되는지에 따라 평가되는지 여부
4. 코멘트가 전적으로 개인 경험에 대한 것이 아니라 일부 객관성에 뿌리를 두어야 하는지 여부(예: 'askscience' 대 'AskAmericans')입니다.
열차/검증/테스트 분할은 하위 레딧의 포스트 ID를 각각 90%/5%/5% 비율로 분할하여 생성되어 여러 분할에 포스트가 나타나지 않는다.
상이한 게시물들은 상이한 수의 코멘트들을 갖기 때문에, 각각의 분할에서의 선호들의 수는 정확히 90%/5%/5%가 아니다:
### 데이터 선택
포스트/댓글의 점수는 1에 사용자로부터의 상향 투표 수(승인)를 곱하고 하향 투표 수(승인 취소)를 뺀 값입니다.
점수의 값은 상대적입니다. 트래픽이 많은 하위 레딧(게시물)에서는 점수가 높은 게시물(댓글)이 더 많습니다.
게시물에서 더 일찍 게시된 댓글은 단순히 노출이 많아 점수가 더 높은 경향이 있을 것이므로 선호도를 추론할 때 타임스탬프 정보를 사용하는 것이 필수적이다.
게시물 P와 두 개의 주석(A,B)이 주어지면 데이터 세트에 선호도 A > B만 포함했다.
1. A는 *늦지 않게* B로 작성되었고 A는 B보다 높은 점수를 갖는다.
2. 게시물은 2023년 이전에 만들어진 셀프-포스트(즉, 텍스트의 본문이고 다른 페이지로의 링크가 아님)이며, 편집되지 않았으며, NSFW(18 초과)가 아니다.
3. 삭제된 사용자, 사회자 또는 게시물 작성자에 의해 어떠한 코멘트도 이루어지지 않았다. 게시물은 삭제된 사용자 또는 진행자가 만들지 않았습니다.
4. 게시물은 점수가 >=10이고 각 코멘트는 점수가 >=2(적어도 한 번 이상 투표)이다.
주석이 있는 게시물은 'n' 데이터에서 최대 ('n' '2') 환경 설정을 선택할 수 있습니다.
게시물당 댓글 수는 파레토 배포이기 때문에 상대적으로 적은 수의 게시물이 데이터를 지배하는 것을 방지하기 위해 게시물당 50개의 댓글으로 스크래핑을 제한했다.
이는 위의 모든 기준을 충족해야 하기 때문에 실제로는 훨씬 적은 수이지만 각 게시물에 데이터 집합에서 최대 ('50' '2'를 선택) 주석이 있을 수 있음을 의미 합니다.
레드딧은 서브레드딧마다 상위 1000개 이상의 게시물을 얻는 것을 매우 어렵게 만든다.
최상위 1,000개의 게시물부터 시작하여 Reddit의 검색 기능을 사용하여 각 게시물과 가장 유사한 25개의 게시물을 검색하여 하위 레딧당 최대 7500개의 고유한 게시물 ID를 얻었다.
### 전처리
전처리를 최소한으로 유지하려고 노력했습니다. 서브레디트-특정 약어는 확장되었다(예를 들어, "CMV"를 "내 견해를 변경"으로).
하이퍼링크에서, 참조 텍스트만이 유지되고 URL이 제거되었다(URL이 기입된 경우, 그것은 유지되었다).
기본 설정 모델 만들기
------------
### Finetuning
인간 선호도(예를 들어, NLG 평가 또는 RLHF 보상 모델에 대해)를 예측하기 위해 모델을 피니튜닝하고자 하는 경우, 여기 몇 가지 유용한 팁이 있다:
1. 데이터를 전처리합니다.\* \* 총 입력 길이는 모델의 토큰 제한 (일반적으로 512 토큰)에 적합 해야 합니다.
FLAN-T5와 같은 모델은 위치 임베딩을 사용하지만 512개 토큰 이상의 입력에서 손실을 조정하면 손실이 수렴하지 않는다는 것을 발견했다.
이를 방지 하려면 게시글 텍스트 ('history' 필드에서)를 가능한 한 잘라서 전체 입력이 512 토큰 아래에 있도록 합니다 (그러나 주석을 잘리지 않음).
여전히 512 토큰 이상이면 예제를 건너뜁니다.
2. 충분히 큰 모델을 사용 합니다.
모든 트레이닝 데이터에 걸쳐 단일 FLAN-T5-xl 모델을 피니튜닝하는 것은 72-73%(전체 입력이 토큰 한계 내에 맞는 예시의 모든 도메인에 걸쳐) 사이의 테스트 정확도를 제공해야 하며, 개별 서브레딧의 경우 65-80% 범위이다.
3. 도메인 내 예측을 수행 합니다.\* \* 하위 레딧이 관련이 없는 경우 도메인 외 성능이 좋지 않습니다 (예: 환경 설정을 미세 조정 하 고 환경 설정을 테스트 하는 경우 'askculinary' 'askcarguys').
4. 더 적은 에폭에 대해 훈련 InstructGPT 종이 페이퍼는 1 에폭에 대해서만 보상 모델을 훈련하는 것을 제안합니다.
동일한 코멘트가 여러 선호도에서 나타나기 때문에 데이터에 과적합되기 쉽다.
5. 더 적은 데이터에 대한 교육이 도움이 될 수 있습니다\* \*.
큰 'score\_ratio'를 사용하는 환경 설정(예: 주석 B의 점수가 2배인 주석 A)은 모델을 조정하기 위한 더 강력한 신호를 제공하므로 특정 이상의 환경 설정만 고려하려는 것일 수 있습니다 'score\_ratio'.
게시물당 선호도 수는 Pareto-distributed이므로 모델이 특정 게시물에 과도하게 적합 하는 것을 방지 하기 위해 특정 게시물에서 선호도 수를 제한 하는 것이 좋습니다.
### 평가
약한 기본 설정보다 강력한 기본 설정을 예측하는 것이 더 쉽기 때문에 단일 정확도 값을 보고하는 대신 성능 곡선을 'score\_ratio'의 함수로 보고하는 것이 좋습니다.
예를 들어, 여기 위의 제안들을 사용하여 질문적 데이터에 대해 트레이닝된 FLAN-T5-xl 모델에 대한 정확도 곡선이 있다.
주황색 라인은 2+ 스코어 비율을 갖는 선호도에만 피니튜닝하고 과적합을 방지하기 위해 각 포스트로부터 5개 이하의 선호도를 사용하는 것이다:
로 이루어진 군에서 선택되는 어느 하나인 것을 특징으로 하는 유기 발광 표시 장치. 그래프
우리는 더 낮지만 더 높은 품질의 데이터를 미세 조정하는 것이 실제 단점이 없는 점수 비율이 3.5 미만인 테스트 데이터에 대한 더 높은 정확도로 이어진다는 것을 알 수 있다!
토큰 제한 내에 입력이 맞지 않는 예는 모델에서 처리할 것으로 예상할 수 없기 때문에 실험에서 제외되었다.
### SteamSHP - Open-Source Preference Model
우리는 SHP 데이터 세트와 Anthropic의 HH-RLHF의 도움 데이터 모두에 대해 두 개의 FLAN-T5 모델을 미세 조정했다. 그들은
* 테스트 데이터에서 72.8%를 달성하는 3B 매개 변수 모델인 SteamSHP-XL입니다.
* 테스트 데이터에서 72.0%를 달성하는 780M 매개 변수 모델인 SteamSHP-Large입니다.
NLG 평가, RLHF에 대한 보상 모델 구축 또는 적합하다고 생각하는 다른 목적으로 스팀SHP를 사용하는 것이 좋습니다!
편향 및 제한 사항
----------
### Biases
NSFW(18세 이상) 콘텐츠로 게시물을 걸러내고, 잘 조정되고 괴롭힘과 편협에 대한 정책이 있는 하위 레딧을 선택했지만 일부 데이터에는 차별적이거나 해로운 언어가 포함될 수 있다.
데이터는 데이터 세트 작성자의 보기를 반영하지 않습니다.
이러한 하위 레딧의 레딧 사용자도 광범위한 모집단을 대표하지 않는다.
하위 레딧별 인구 통계 정보는 사용할 수 없지만 전체 레딧 사용자는 불균형적으로 남성이며 선진국, 서양 및 영어 사용 국가에서 왔습니다 (Pew Research).
이 데이터에 대해 학습된 모델을 사용하기 전에 이 점을 염두에 두십시오.
### 제한 사항
SHP의 선호도 레이블은 지시/질문이 주어졌을 때 한 응답이 다른 응답과 얼마나 *도움이* 되는지 반영 하기 위한 것입니다.
SHP는 좋은 독성 검출기를 배우는 데 필요한 독성 함량을 포함하도록 설계되지 않았기 때문에 위해 최소화에서 사용하기 위한 것이 아니다.
환경 설정 레이블이 더 적은 해를 나타내는 데이터를 찾는 경우 Anthropic의 HH-RLHF의 유해성 분할을 권장합니다.
또 다른 한계는 SHP에서 선호되는 응답이 반드시 더 사실적인 응답은 아니라는 것이다.
일부 논평은 그들의 반응을 정당화하기 위해 인용을 제공하지만 대부분은 그렇지 않다.
여기에는 'askhistorians' 하위 레딧과 같은 예외가 있으며, 이는 크게 조정되며 답변이 인용을 제공할 것으로 예상된다.
SHP의 집단 선호도 라벨은 가중치가 없는 합계를 취하기 전에 사용자에게 각 코멘트에 독립적으로 투표하도록 요청하면 반드시 얻을 수 있는 것은 아니다.
Reddit에 대한 주석 점수는 공개적이며 사용자 환경 설정에 영향을 미치는 것으로 알려져 있기 때문입니다. 높은 점수는 (Muchnik et al., 2013)보다 긍정적인 표를 얻을 가능성을 높입니다.
이 "허딩 효과"가 사용자의 선호도를 일시적으로 또는 영구적으로 이동시키는지 여부는 불분명하다.
따라서, SHP가 집단적 인간 선호도를 반영하지만, SHP에 대해 훈련된 모델은 개별 선호도가 다르게 집계되는 설정으로 일반화되지 않을 수 있다(예를 들어, 사용자는 현재 코멘트 점수를 전혀 보지 않고 독립적으로 투표하고, 사용자는 부여 후 투표 등).
그렉 스토다드가 지적해줘서 고마워요
License
-------
Last updated: 03/01/2023
이 데이터 세트는 Reddit과 직접 통신 또는 서면 동의 없이 Reddit API 사용 약관에 따라 Reddit을 스크래핑하여 만들었습니다.
사용 약관에 따라 "사용자 콘텐츠"는 Reddit이 아닌 사용자 자신이 소유하고 있으며 Reddit은 "사용자 콘텐츠를 복사 및 표시 하기 위해 독점적이지 않고 양도할 수 없으며 공개되지 않으며 취소할 수 있는 라이선스"를 부여 합니다.
Reddit을 스크래핑 하 여 만든 데이터 집합은 연구 커뮤니티에서 널리 사용 됩니다. 예를 들어 Facebook AI 리서치는 Reddit에서 스크래핑 된 데이터를 사용 하 여 라이선스 없이 사용 하도록 만든 2019년 ELI5 데이터 집합을 만들었습니다.
인류성 AI는 다른 방법론을 사용 하 여 환경 설정에 대 한 Reddit을 스크래핑 합니다. 그러나이 데이터는 공개 되지 않았습니다.
정기적인 일정에서 Reddit의 전체 덤프를 사용할 수 있도록 하는 PushShift Reddit 데이터 세트도 라이선스 없이 사용할 수 있습니다 (알고 있는 범위).
우리는 책임을 지지 않으며 이 데이터 세트의 다운스트림 사용을 명시적으로 또는 암시적으로 지지하지 않는다.
우리는 향후 어느 시점에서든 SHP 데이터 세트와 이 라이선스를 수정할 수 있는 권한을 보유합니다.
Contact
-------
데이터에 대한 질문이 있는 경우 [email protected]에 문의하십시오.
이 데이터 세트는 카윈 에타야라흐, 하이디(첸유) 장, 이중 왕 및 단 주라프스키에 의해 생성되었다.
인용
--
SHP는 다음 논문에서 제안한 기법을 이용하여 생성하였다. SHP 또는 스팀SHP 모델을 사용하는 경우 이 작업을 인용하십시오.
참조
--
Ethayarajh, K., Choi, Y. & Swayamdipta, S. (2022). Understanding Dataset Difficulty with $\mathcal{V}$-Usable Information. *Proceedings of the 39th International Conference on Machine Learning*, in *Proceedings of Machine Learning Research*. 162:5988-6008 Available from URL
| [
"# positive votes - # negative votes + 1) received by comment A (integer)\n* : (# positive votes - # negative votes + 1) received by comment B (integer)\n* : comment A의 텍스트 (string)\n* : comment B의 텍스트 (string)\n* : 선호도 레이블 -- A가 B보다 선호되는 경우 1이고, B가 A보다 선호되는 경우 0입니다. 레이블 분포가 대략 50/50이 되도록 무작위화되었습니다. (정수)\n* : 덜 선호되는 코멘트가 생성된 후 몇 초 후에 더 선호되는 코멘트가 생성되었는지(항상 >= 0일 것임) (정수)\n* : 더 선호하는 댓글의 점수와 덜 선호하는 댓글의 점수의 비율 (>= 1) (float)\n\n\nDataset Design\n--------------",
"### 도메인 선택\n\n\n데이터는 *서브레딧* 이라는 토픽별 포라로 구성된 공개 포럼인 Reddit에서 공급됩니다.\n예를 들어 'askculinary' 하위 레딧은 사용자가 요리 관련 질문을 하고 다른 사용자에 의해 응답 되는 것입니다.\n\n\nSHP에는 18개의 다른 하위 레딧에서 긁어낸 주석에 대한 열차, 유효성 검사 및 테스트 분할이 포함되어 있습니다. 우리는 다음을 기반으로 하위 레딧을 선택했습니다.\n\n\n1. 잘 알려진 것인지 여부(가입자수 >= 100K)\n2. 게시물이 질문 또는 지시를 내릴 것으로 예상되었는지 여부\n3. 응답이 얼마나 *도움이* 되는지에 따라 평가되는지 여부\n4. 코멘트가 전적으로 개인 경험에 대한 것이 아니라 일부 객관성에 뿌리를 두어야 하는지 여부(예: 'askscience' 대 'AskAmericans')입니다.\n\n\n열차/검증/테스트 분할은 하위 레딧의 포스트 ID를 각각 90%/5%/5% 비율로 분할하여 생성되어 여러 분할에 포스트가 나타나지 않는다.\n상이한 게시물들은 상이한 수의 코멘트들을 갖기 때문에, 각각의 분할에서의 선호들의 수는 정확히 90%/5%/5%가 아니다:",
"### 데이터 선택\n\n\n포스트/댓글의 점수는 1에 사용자로부터의 상향 투표 수(승인)를 곱하고 하향 투표 수(승인 취소)를 뺀 값입니다.\n점수의 값은 상대적입니다. 트래픽이 많은 하위 레딧(게시물)에서는 점수가 높은 게시물(댓글)이 더 많습니다.\n게시물에서 더 일찍 게시된 댓글은 단순히 노출이 많아 점수가 더 높은 경향이 있을 것이므로 선호도를 추론할 때 타임스탬프 정보를 사용하는 것이 필수적이다.\n\n\n게시물 P와 두 개의 주석(A,B)이 주어지면 데이터 세트에 선호도 A > B만 포함했다.\n\n\n1. A는 *늦지 않게* B로 작성되었고 A는 B보다 높은 점수를 갖는다.\n2. 게시물은 2023년 이전에 만들어진 셀프-포스트(즉, 텍스트의 본문이고 다른 페이지로의 링크가 아님)이며, 편집되지 않았으며, NSFW(18 초과)가 아니다.\n3. 삭제된 사용자, 사회자 또는 게시물 작성자에 의해 어떠한 코멘트도 이루어지지 않았다. 게시물은 삭제된 사용자 또는 진행자가 만들지 않았습니다.\n4. 게시물은 점수가 >=10이고 각 코멘트는 점수가 >=2(적어도 한 번 이상 투표)이다.\n\n\n주석이 있는 게시물은 'n' 데이터에서 최대 ('n' '2') 환경 설정을 선택할 수 있습니다.\n게시물당 댓글 수는 파레토 배포이기 때문에 상대적으로 적은 수의 게시물이 데이터를 지배하는 것을 방지하기 위해 게시물당 50개의 댓글으로 스크래핑을 제한했다.\n이는 위의 모든 기준을 충족해야 하기 때문에 실제로는 훨씬 적은 수이지만 각 게시물에 데이터 집합에서 최대 ('50' '2'를 선택) 주석이 있을 수 있음을 의미 합니다.\n\n\n레드딧은 서브레드딧마다 상위 1000개 이상의 게시물을 얻는 것을 매우 어렵게 만든다.\n최상위 1,000개의 게시물부터 시작하여 Reddit의 검색 기능을 사용하여 각 게시물과 가장 유사한 25개의 게시물을 검색하여 하위 레딧당 최대 7500개의 고유한 게시물 ID를 얻었다.",
"### 전처리\n\n\n전처리를 최소한으로 유지하려고 노력했습니다. 서브레디트-특정 약어는 확장되었다(예를 들어, \"CMV\"를 \"내 견해를 변경\"으로).\n하이퍼링크에서, 참조 텍스트만이 유지되고 URL이 제거되었다(URL이 기입된 경우, 그것은 유지되었다).\n\n\n기본 설정 모델 만들기\n------------",
"### Finetuning\n\n\n인간 선호도(예를 들어, NLG 평가 또는 RLHF 보상 모델에 대해)를 예측하기 위해 모델을 피니튜닝하고자 하는 경우, 여기 몇 가지 유용한 팁이 있다:\n\n\n1. 데이터를 전처리합니다.\\* \\* 총 입력 길이는 모델의 토큰 제한 (일반적으로 512 토큰)에 적합 해야 합니다.\nFLAN-T5와 같은 모델은 위치 임베딩을 사용하지만 512개 토큰 이상의 입력에서 손실을 조정하면 손실이 수렴하지 않는다는 것을 발견했다.\n이를 방지 하려면 게시글 텍스트 ('history' 필드에서)를 가능한 한 잘라서 전체 입력이 512 토큰 아래에 있도록 합니다 (그러나 주석을 잘리지 않음).\n여전히 512 토큰 이상이면 예제를 건너뜁니다.\n2. 충분히 큰 모델을 사용 합니다.\n모든 트레이닝 데이터에 걸쳐 단일 FLAN-T5-xl 모델을 피니튜닝하는 것은 72-73%(전체 입력이 토큰 한계 내에 맞는 예시의 모든 도메인에 걸쳐) 사이의 테스트 정확도를 제공해야 하며, 개별 서브레딧의 경우 65-80% 범위이다.\n3. 도메인 내 예측을 수행 합니다.\\* \\* 하위 레딧이 관련이 없는 경우 도메인 외 성능이 좋지 않습니다 (예: 환경 설정을 미세 조정 하 고 환경 설정을 테스트 하는 경우 'askculinary' 'askcarguys').\n4. 더 적은 에폭에 대해 훈련 InstructGPT 종이 페이퍼는 1 에폭에 대해서만 보상 모델을 훈련하는 것을 제안합니다.\n동일한 코멘트가 여러 선호도에서 나타나기 때문에 데이터에 과적합되기 쉽다.\n5. 더 적은 데이터에 대한 교육이 도움이 될 수 있습니다\\* \\*.\n큰 'score\\_ratio'를 사용하는 환경 설정(예: 주석 B의 점수가 2배인 주석 A)은 모델을 조정하기 위한 더 강력한 신호를 제공하므로 특정 이상의 환경 설정만 고려하려는 것일 수 있습니다 'score\\_ratio'.\n게시물당 선호도 수는 Pareto-distributed이므로 모델이 특정 게시물에 과도하게 적합 하는 것을 방지 하기 위해 특정 게시물에서 선호도 수를 제한 하는 것이 좋습니다.",
"### 평가\n\n\n약한 기본 설정보다 강력한 기본 설정을 예측하는 것이 더 쉽기 때문에 단일 정확도 값을 보고하는 대신 성능 곡선을 'score\\_ratio'의 함수로 보고하는 것이 좋습니다.\n예를 들어, 여기 위의 제안들을 사용하여 질문적 데이터에 대해 트레이닝된 FLAN-T5-xl 모델에 대한 정확도 곡선이 있다.\n주황색 라인은 2+ 스코어 비율을 갖는 선호도에만 피니튜닝하고 과적합을 방지하기 위해 각 포스트로부터 5개 이하의 선호도를 사용하는 것이다:\n\n\n로 이루어진 군에서 선택되는 어느 하나인 것을 특징으로 하는 유기 발광 표시 장치. 그래프\n\n\n우리는 더 낮지만 더 높은 품질의 데이터를 미세 조정하는 것이 실제 단점이 없는 점수 비율이 3.5 미만인 테스트 데이터에 대한 더 높은 정확도로 이어진다는 것을 알 수 있다!\n토큰 제한 내에 입력이 맞지 않는 예는 모델에서 처리할 것으로 예상할 수 없기 때문에 실험에서 제외되었다.",
"### SteamSHP - Open-Source Preference Model\n\n\n우리는 SHP 데이터 세트와 Anthropic의 HH-RLHF의 도움 데이터 모두에 대해 두 개의 FLAN-T5 모델을 미세 조정했다. 그들은\n\n\n* 테스트 데이터에서 72.8%를 달성하는 3B 매개 변수 모델인 SteamSHP-XL입니다.\n* 테스트 데이터에서 72.0%를 달성하는 780M 매개 변수 모델인 SteamSHP-Large입니다.\n\n\nNLG 평가, RLHF에 대한 보상 모델 구축 또는 적합하다고 생각하는 다른 목적으로 스팀SHP를 사용하는 것이 좋습니다!\n\n\n편향 및 제한 사항\n----------",
"### Biases\n\n\nNSFW(18세 이상) 콘텐츠로 게시물을 걸러내고, 잘 조정되고 괴롭힘과 편협에 대한 정책이 있는 하위 레딧을 선택했지만 일부 데이터에는 차별적이거나 해로운 언어가 포함될 수 있다.\n데이터는 데이터 세트 작성자의 보기를 반영하지 않습니다.\n이러한 하위 레딧의 레딧 사용자도 광범위한 모집단을 대표하지 않는다.\n하위 레딧별 인구 통계 정보는 사용할 수 없지만 전체 레딧 사용자는 불균형적으로 남성이며 선진국, 서양 및 영어 사용 국가에서 왔습니다 (Pew Research).\n이 데이터에 대해 학습된 모델을 사용하기 전에 이 점을 염두에 두십시오.",
"### 제한 사항\n\n\nSHP의 선호도 레이블은 지시/질문이 주어졌을 때 한 응답이 다른 응답과 얼마나 *도움이* 되는지 반영 하기 위한 것입니다.\nSHP는 좋은 독성 검출기를 배우는 데 필요한 독성 함량을 포함하도록 설계되지 않았기 때문에 위해 최소화에서 사용하기 위한 것이 아니다.\n환경 설정 레이블이 더 적은 해를 나타내는 데이터를 찾는 경우 Anthropic의 HH-RLHF의 유해성 분할을 권장합니다.\n\n\n또 다른 한계는 SHP에서 선호되는 응답이 반드시 더 사실적인 응답은 아니라는 것이다.\n일부 논평은 그들의 반응을 정당화하기 위해 인용을 제공하지만 대부분은 그렇지 않다.\n여기에는 'askhistorians' 하위 레딧과 같은 예외가 있으며, 이는 크게 조정되며 답변이 인용을 제공할 것으로 예상된다.\n\n\nSHP의 집단 선호도 라벨은 가중치가 없는 합계를 취하기 전에 사용자에게 각 코멘트에 독립적으로 투표하도록 요청하면 반드시 얻을 수 있는 것은 아니다.\nReddit에 대한 주석 점수는 공개적이며 사용자 환경 설정에 영향을 미치는 것으로 알려져 있기 때문입니다. 높은 점수는 (Muchnik et al., 2013)보다 긍정적인 표를 얻을 가능성을 높입니다.\n이 \"허딩 효과\"가 사용자의 선호도를 일시적으로 또는 영구적으로 이동시키는지 여부는 불분명하다.\n따라서, SHP가 집단적 인간 선호도를 반영하지만, SHP에 대해 훈련된 모델은 개별 선호도가 다르게 집계되는 설정으로 일반화되지 않을 수 있다(예를 들어, 사용자는 현재 코멘트 점수를 전혀 보지 않고 독립적으로 투표하고, 사용자는 부여 후 투표 등).\n그렉 스토다드가 지적해줘서 고마워요\n\n\nLicense\n-------\n\n\nLast updated: 03/01/2023\n\n\n이 데이터 세트는 Reddit과 직접 통신 또는 서면 동의 없이 Reddit API 사용 약관에 따라 Reddit을 스크래핑하여 만들었습니다.\n사용 약관에 따라 \"사용자 콘텐츠\"는 Reddit이 아닌 사용자 자신이 소유하고 있으며 Reddit은 \"사용자 콘텐츠를 복사 및 표시 하기 위해 독점적이지 않고 양도할 수 없으며 공개되지 않으며 취소할 수 있는 라이선스\"를 부여 합니다.\n\n\nReddit을 스크래핑 하 여 만든 데이터 집합은 연구 커뮤니티에서 널리 사용 됩니다. 예를 들어 Facebook AI 리서치는 Reddit에서 스크래핑 된 데이터를 사용 하 여 라이선스 없이 사용 하도록 만든 2019년 ELI5 데이터 집합을 만들었습니다.\n인류성 AI는 다른 방법론을 사용 하 여 환경 설정에 대 한 Reddit을 스크래핑 합니다. 그러나이 데이터는 공개 되지 않았습니다.\n정기적인 일정에서 Reddit의 전체 덤프를 사용할 수 있도록 하는 PushShift Reddit 데이터 세트도 라이선스 없이 사용할 수 있습니다 (알고 있는 범위).\n\n\n우리는 책임을 지지 않으며 이 데이터 세트의 다운스트림 사용을 명시적으로 또는 암시적으로 지지하지 않는다.\n우리는 향후 어느 시점에서든 SHP 데이터 세트와 이 라이선스를 수정할 수 있는 권한을 보유합니다.\n\n\nContact\n-------\n\n\n데이터에 대한 질문이 있는 경우 [email protected]에 문의하십시오.\n이 데이터 세트는 카윈 에타야라흐, 하이디(첸유) 장, 이중 왕 및 단 주라프스키에 의해 생성되었다.\n\n\n인용\n--\n\n\nSHP는 다음 논문에서 제안한 기법을 이용하여 생성하였다. SHP 또는 스팀SHP 모델을 사용하는 경우 이 작업을 인용하십시오.\n\n\n참조\n--\n\n\nEthayarajh, K., Choi, Y. & Swayamdipta, S. (2022). Understanding Dataset Difficulty with $\\mathcal{V}$-Usable Information. *Proceedings of the 39th International Conference on Machine Learning*, in *Proceedings of Machine Learning Research*. 162:5988-6008 Available from URL"
] | [
"TAGS\n#task_categories-text-generation #task_categories-question-answering #size_categories-100K<n<1M #language-Korean #language-English #license-cc-by-nc-sa-4.0 #human feedback #rlhf #preferences #reddit #preference model #RL #NLG #evaluation #arxiv-2112.00861 #arxiv-2001.08435 #region-us \n",
"# positive votes - # negative votes + 1) received by comment A (integer)\n* : (# positive votes - # negative votes + 1) received by comment B (integer)\n* : comment A의 텍스트 (string)\n* : comment B의 텍스트 (string)\n* : 선호도 레이블 -- A가 B보다 선호되는 경우 1이고, B가 A보다 선호되는 경우 0입니다. 레이블 분포가 대략 50/50이 되도록 무작위화되었습니다. (정수)\n* : 덜 선호되는 코멘트가 생성된 후 몇 초 후에 더 선호되는 코멘트가 생성되었는지(항상 >= 0일 것임) (정수)\n* : 더 선호하는 댓글의 점수와 덜 선호하는 댓글의 점수의 비율 (>= 1) (float)\n\n\nDataset Design\n--------------",
"### 도메인 선택\n\n\n데이터는 *서브레딧* 이라는 토픽별 포라로 구성된 공개 포럼인 Reddit에서 공급됩니다.\n예를 들어 'askculinary' 하위 레딧은 사용자가 요리 관련 질문을 하고 다른 사용자에 의해 응답 되는 것입니다.\n\n\nSHP에는 18개의 다른 하위 레딧에서 긁어낸 주석에 대한 열차, 유효성 검사 및 테스트 분할이 포함되어 있습니다. 우리는 다음을 기반으로 하위 레딧을 선택했습니다.\n\n\n1. 잘 알려진 것인지 여부(가입자수 >= 100K)\n2. 게시물이 질문 또는 지시를 내릴 것으로 예상되었는지 여부\n3. 응답이 얼마나 *도움이* 되는지에 따라 평가되는지 여부\n4. 코멘트가 전적으로 개인 경험에 대한 것이 아니라 일부 객관성에 뿌리를 두어야 하는지 여부(예: 'askscience' 대 'AskAmericans')입니다.\n\n\n열차/검증/테스트 분할은 하위 레딧의 포스트 ID를 각각 90%/5%/5% 비율로 분할하여 생성되어 여러 분할에 포스트가 나타나지 않는다.\n상이한 게시물들은 상이한 수의 코멘트들을 갖기 때문에, 각각의 분할에서의 선호들의 수는 정확히 90%/5%/5%가 아니다:",
"### 데이터 선택\n\n\n포스트/댓글의 점수는 1에 사용자로부터의 상향 투표 수(승인)를 곱하고 하향 투표 수(승인 취소)를 뺀 값입니다.\n점수의 값은 상대적입니다. 트래픽이 많은 하위 레딧(게시물)에서는 점수가 높은 게시물(댓글)이 더 많습니다.\n게시물에서 더 일찍 게시된 댓글은 단순히 노출이 많아 점수가 더 높은 경향이 있을 것이므로 선호도를 추론할 때 타임스탬프 정보를 사용하는 것이 필수적이다.\n\n\n게시물 P와 두 개의 주석(A,B)이 주어지면 데이터 세트에 선호도 A > B만 포함했다.\n\n\n1. A는 *늦지 않게* B로 작성되었고 A는 B보다 높은 점수를 갖는다.\n2. 게시물은 2023년 이전에 만들어진 셀프-포스트(즉, 텍스트의 본문이고 다른 페이지로의 링크가 아님)이며, 편집되지 않았으며, NSFW(18 초과)가 아니다.\n3. 삭제된 사용자, 사회자 또는 게시물 작성자에 의해 어떠한 코멘트도 이루어지지 않았다. 게시물은 삭제된 사용자 또는 진행자가 만들지 않았습니다.\n4. 게시물은 점수가 >=10이고 각 코멘트는 점수가 >=2(적어도 한 번 이상 투표)이다.\n\n\n주석이 있는 게시물은 'n' 데이터에서 최대 ('n' '2') 환경 설정을 선택할 수 있습니다.\n게시물당 댓글 수는 파레토 배포이기 때문에 상대적으로 적은 수의 게시물이 데이터를 지배하는 것을 방지하기 위해 게시물당 50개의 댓글으로 스크래핑을 제한했다.\n이는 위의 모든 기준을 충족해야 하기 때문에 실제로는 훨씬 적은 수이지만 각 게시물에 데이터 집합에서 최대 ('50' '2'를 선택) 주석이 있을 수 있음을 의미 합니다.\n\n\n레드딧은 서브레드딧마다 상위 1000개 이상의 게시물을 얻는 것을 매우 어렵게 만든다.\n최상위 1,000개의 게시물부터 시작하여 Reddit의 검색 기능을 사용하여 각 게시물과 가장 유사한 25개의 게시물을 검색하여 하위 레딧당 최대 7500개의 고유한 게시물 ID를 얻었다.",
"### 전처리\n\n\n전처리를 최소한으로 유지하려고 노력했습니다. 서브레디트-특정 약어는 확장되었다(예를 들어, \"CMV\"를 \"내 견해를 변경\"으로).\n하이퍼링크에서, 참조 텍스트만이 유지되고 URL이 제거되었다(URL이 기입된 경우, 그것은 유지되었다).\n\n\n기본 설정 모델 만들기\n------------",
"### Finetuning\n\n\n인간 선호도(예를 들어, NLG 평가 또는 RLHF 보상 모델에 대해)를 예측하기 위해 모델을 피니튜닝하고자 하는 경우, 여기 몇 가지 유용한 팁이 있다:\n\n\n1. 데이터를 전처리합니다.\\* \\* 총 입력 길이는 모델의 토큰 제한 (일반적으로 512 토큰)에 적합 해야 합니다.\nFLAN-T5와 같은 모델은 위치 임베딩을 사용하지만 512개 토큰 이상의 입력에서 손실을 조정하면 손실이 수렴하지 않는다는 것을 발견했다.\n이를 방지 하려면 게시글 텍스트 ('history' 필드에서)를 가능한 한 잘라서 전체 입력이 512 토큰 아래에 있도록 합니다 (그러나 주석을 잘리지 않음).\n여전히 512 토큰 이상이면 예제를 건너뜁니다.\n2. 충분히 큰 모델을 사용 합니다.\n모든 트레이닝 데이터에 걸쳐 단일 FLAN-T5-xl 모델을 피니튜닝하는 것은 72-73%(전체 입력이 토큰 한계 내에 맞는 예시의 모든 도메인에 걸쳐) 사이의 테스트 정확도를 제공해야 하며, 개별 서브레딧의 경우 65-80% 범위이다.\n3. 도메인 내 예측을 수행 합니다.\\* \\* 하위 레딧이 관련이 없는 경우 도메인 외 성능이 좋지 않습니다 (예: 환경 설정을 미세 조정 하 고 환경 설정을 테스트 하는 경우 'askculinary' 'askcarguys').\n4. 더 적은 에폭에 대해 훈련 InstructGPT 종이 페이퍼는 1 에폭에 대해서만 보상 모델을 훈련하는 것을 제안합니다.\n동일한 코멘트가 여러 선호도에서 나타나기 때문에 데이터에 과적합되기 쉽다.\n5. 더 적은 데이터에 대한 교육이 도움이 될 수 있습니다\\* \\*.\n큰 'score\\_ratio'를 사용하는 환경 설정(예: 주석 B의 점수가 2배인 주석 A)은 모델을 조정하기 위한 더 강력한 신호를 제공하므로 특정 이상의 환경 설정만 고려하려는 것일 수 있습니다 'score\\_ratio'.\n게시물당 선호도 수는 Pareto-distributed이므로 모델이 특정 게시물에 과도하게 적합 하는 것을 방지 하기 위해 특정 게시물에서 선호도 수를 제한 하는 것이 좋습니다.",
"### 평가\n\n\n약한 기본 설정보다 강력한 기본 설정을 예측하는 것이 더 쉽기 때문에 단일 정확도 값을 보고하는 대신 성능 곡선을 'score\\_ratio'의 함수로 보고하는 것이 좋습니다.\n예를 들어, 여기 위의 제안들을 사용하여 질문적 데이터에 대해 트레이닝된 FLAN-T5-xl 모델에 대한 정확도 곡선이 있다.\n주황색 라인은 2+ 스코어 비율을 갖는 선호도에만 피니튜닝하고 과적합을 방지하기 위해 각 포스트로부터 5개 이하의 선호도를 사용하는 것이다:\n\n\n로 이루어진 군에서 선택되는 어느 하나인 것을 특징으로 하는 유기 발광 표시 장치. 그래프\n\n\n우리는 더 낮지만 더 높은 품질의 데이터를 미세 조정하는 것이 실제 단점이 없는 점수 비율이 3.5 미만인 테스트 데이터에 대한 더 높은 정확도로 이어진다는 것을 알 수 있다!\n토큰 제한 내에 입력이 맞지 않는 예는 모델에서 처리할 것으로 예상할 수 없기 때문에 실험에서 제외되었다.",
"### SteamSHP - Open-Source Preference Model\n\n\n우리는 SHP 데이터 세트와 Anthropic의 HH-RLHF의 도움 데이터 모두에 대해 두 개의 FLAN-T5 모델을 미세 조정했다. 그들은\n\n\n* 테스트 데이터에서 72.8%를 달성하는 3B 매개 변수 모델인 SteamSHP-XL입니다.\n* 테스트 데이터에서 72.0%를 달성하는 780M 매개 변수 모델인 SteamSHP-Large입니다.\n\n\nNLG 평가, RLHF에 대한 보상 모델 구축 또는 적합하다고 생각하는 다른 목적으로 스팀SHP를 사용하는 것이 좋습니다!\n\n\n편향 및 제한 사항\n----------",
"### Biases\n\n\nNSFW(18세 이상) 콘텐츠로 게시물을 걸러내고, 잘 조정되고 괴롭힘과 편협에 대한 정책이 있는 하위 레딧을 선택했지만 일부 데이터에는 차별적이거나 해로운 언어가 포함될 수 있다.\n데이터는 데이터 세트 작성자의 보기를 반영하지 않습니다.\n이러한 하위 레딧의 레딧 사용자도 광범위한 모집단을 대표하지 않는다.\n하위 레딧별 인구 통계 정보는 사용할 수 없지만 전체 레딧 사용자는 불균형적으로 남성이며 선진국, 서양 및 영어 사용 국가에서 왔습니다 (Pew Research).\n이 데이터에 대해 학습된 모델을 사용하기 전에 이 점을 염두에 두십시오.",
"### 제한 사항\n\n\nSHP의 선호도 레이블은 지시/질문이 주어졌을 때 한 응답이 다른 응답과 얼마나 *도움이* 되는지 반영 하기 위한 것입니다.\nSHP는 좋은 독성 검출기를 배우는 데 필요한 독성 함량을 포함하도록 설계되지 않았기 때문에 위해 최소화에서 사용하기 위한 것이 아니다.\n환경 설정 레이블이 더 적은 해를 나타내는 데이터를 찾는 경우 Anthropic의 HH-RLHF의 유해성 분할을 권장합니다.\n\n\n또 다른 한계는 SHP에서 선호되는 응답이 반드시 더 사실적인 응답은 아니라는 것이다.\n일부 논평은 그들의 반응을 정당화하기 위해 인용을 제공하지만 대부분은 그렇지 않다.\n여기에는 'askhistorians' 하위 레딧과 같은 예외가 있으며, 이는 크게 조정되며 답변이 인용을 제공할 것으로 예상된다.\n\n\nSHP의 집단 선호도 라벨은 가중치가 없는 합계를 취하기 전에 사용자에게 각 코멘트에 독립적으로 투표하도록 요청하면 반드시 얻을 수 있는 것은 아니다.\nReddit에 대한 주석 점수는 공개적이며 사용자 환경 설정에 영향을 미치는 것으로 알려져 있기 때문입니다. 높은 점수는 (Muchnik et al., 2013)보다 긍정적인 표를 얻을 가능성을 높입니다.\n이 \"허딩 효과\"가 사용자의 선호도를 일시적으로 또는 영구적으로 이동시키는지 여부는 불분명하다.\n따라서, SHP가 집단적 인간 선호도를 반영하지만, SHP에 대해 훈련된 모델은 개별 선호도가 다르게 집계되는 설정으로 일반화되지 않을 수 있다(예를 들어, 사용자는 현재 코멘트 점수를 전혀 보지 않고 독립적으로 투표하고, 사용자는 부여 후 투표 등).\n그렉 스토다드가 지적해줘서 고마워요\n\n\nLicense\n-------\n\n\nLast updated: 03/01/2023\n\n\n이 데이터 세트는 Reddit과 직접 통신 또는 서면 동의 없이 Reddit API 사용 약관에 따라 Reddit을 스크래핑하여 만들었습니다.\n사용 약관에 따라 \"사용자 콘텐츠\"는 Reddit이 아닌 사용자 자신이 소유하고 있으며 Reddit은 \"사용자 콘텐츠를 복사 및 표시 하기 위해 독점적이지 않고 양도할 수 없으며 공개되지 않으며 취소할 수 있는 라이선스\"를 부여 합니다.\n\n\nReddit을 스크래핑 하 여 만든 데이터 집합은 연구 커뮤니티에서 널리 사용 됩니다. 예를 들어 Facebook AI 리서치는 Reddit에서 스크래핑 된 데이터를 사용 하 여 라이선스 없이 사용 하도록 만든 2019년 ELI5 데이터 집합을 만들었습니다.\n인류성 AI는 다른 방법론을 사용 하 여 환경 설정에 대 한 Reddit을 스크래핑 합니다. 그러나이 데이터는 공개 되지 않았습니다.\n정기적인 일정에서 Reddit의 전체 덤프를 사용할 수 있도록 하는 PushShift Reddit 데이터 세트도 라이선스 없이 사용할 수 있습니다 (알고 있는 범위).\n\n\n우리는 책임을 지지 않으며 이 데이터 세트의 다운스트림 사용을 명시적으로 또는 암시적으로 지지하지 않는다.\n우리는 향후 어느 시점에서든 SHP 데이터 세트와 이 라이선스를 수정할 수 있는 권한을 보유합니다.\n\n\nContact\n-------\n\n\n데이터에 대한 질문이 있는 경우 [email protected]에 문의하십시오.\n이 데이터 세트는 카윈 에타야라흐, 하이디(첸유) 장, 이중 왕 및 단 주라프스키에 의해 생성되었다.\n\n\n인용\n--\n\n\nSHP는 다음 논문에서 제안한 기법을 이용하여 생성하였다. SHP 또는 스팀SHP 모델을 사용하는 경우 이 작업을 인용하십시오.\n\n\n참조\n--\n\n\nEthayarajh, K., Choi, Y. & Swayamdipta, S. (2022). Understanding Dataset Difficulty with $\\mathcal{V}$-Usable Information. *Proceedings of the 39th International Conference on Machine Learning*, in *Proceedings of Machine Learning Research*. 162:5988-6008 Available from URL"
] | [
107,
186,
283,
481,
80,
511,
228,
137,
153,
858
] | [
"passage: TAGS\n#task_categories-text-generation #task_categories-question-answering #size_categories-100K<n<1M #language-Korean #language-English #license-cc-by-nc-sa-4.0 #human feedback #rlhf #preferences #reddit #preference model #RL #NLG #evaluation #arxiv-2112.00861 #arxiv-2001.08435 #region-us \n# positive votes - # negative votes + 1) received by comment A (integer)\n* : (# positive votes - # negative votes + 1) received by comment B (integer)\n* : comment A의 텍스트 (string)\n* : comment B의 텍스트 (string)\n* : 선호도 레이블 -- A가 B보다 선호되는 경우 1이고, B가 A보다 선호되는 경우 0입니다. 레이블 분포가 대략 50/50이 되도록 무작위화되었습니다. (정수)\n* : 덜 선호되는 코멘트가 생성된 후 몇 초 후에 더 선호되는 코멘트가 생성되었는지(항상 >= 0일 것임) (정수)\n* : 더 선호하는 댓글의 점수와 덜 선호하는 댓글의 점수의 비율 (>= 1) (float)\n\n\nDataset Design\n--------------",
"passage: ### 도메인 선택\n\n\n데이터는 *서브레딧* 이라는 토픽별 포라로 구성된 공개 포럼인 Reddit에서 공급됩니다.\n예를 들어 'askculinary' 하위 레딧은 사용자가 요리 관련 질문을 하고 다른 사용자에 의해 응답 되는 것입니다.\n\n\nSHP에는 18개의 다른 하위 레딧에서 긁어낸 주석에 대한 열차, 유효성 검사 및 테스트 분할이 포함되어 있습니다. 우리는 다음을 기반으로 하위 레딧을 선택했습니다.\n\n\n1. 잘 알려진 것인지 여부(가입자수 >= 100K)\n2. 게시물이 질문 또는 지시를 내릴 것으로 예상되었는지 여부\n3. 응답이 얼마나 *도움이* 되는지에 따라 평가되는지 여부\n4. 코멘트가 전적으로 개인 경험에 대한 것이 아니라 일부 객관성에 뿌리를 두어야 하는지 여부(예: 'askscience' 대 'AskAmericans')입니다.\n\n\n열차/검증/테스트 분할은 하위 레딧의 포스트 ID를 각각 90%/5%/5% 비율로 분할하여 생성되어 여러 분할에 포스트가 나타나지 않는다.\n상이한 게시물들은 상이한 수의 코멘트들을 갖기 때문에, 각각의 분할에서의 선호들의 수는 정확히 90%/5%/5%가 아니다:### 데이터 선택\n\n\n포스트/댓글의 점수는 1에 사용자로부터의 상향 투표 수(승인)를 곱하고 하향 투표 수(승인 취소)를 뺀 값입니다.\n점수의 값은 상대적입니다. 트래픽이 많은 하위 레딧(게시물)에서는 점수가 높은 게시물(댓글)이 더 많습니다.\n게시물에서 더 일찍 게시된 댓글은 단순히 노출이 많아 점수가 더 높은 경향이 있을 것이므로 선호도를 추론할 때 타임스탬프 정보를 사용하는 것이 필수적이다.\n\n\n게시물 P와 두 개의 주석(A,B)이 주어지면 데이터 세트에 선호도 A > B만 포함했다.\n\n\n1. A는 *늦지 않게* B로 작성되었고 A는 B보다 높은 점수를 갖는다.\n2. 게시물은 2023년 이전에 만들어진 셀프-포스트(즉, 텍스트의 본문이고 다른 페이지로의 링크가 아님)이며, 편집되지 않았으며, NSFW(18 초과)가 아니다.\n3. 삭제된 사용자, 사회자 또는 게시물 작성자에 의해 어떠한 코멘트도 이루어지지 않았다. 게시물은 삭제된 사용자 또는 진행자가 만들지 않았습니다.\n4. 게시물은 점수가 >=10이고 각 코멘트는 점수가 >=2(적어도 한 번 이상 투표)이다.\n\n\n주석이 있는 게시물은 'n' 데이터에서 최대 ('n' '2') 환경 설정을 선택할 수 있습니다.\n게시물당 댓글 수는 파레토 배포이기 때문에 상대적으로 적은 수의 게시물이 데이터를 지배하는 것을 방지하기 위해 게시물당 50개의 댓글으로 스크래핑을 제한했다.\n이는 위의 모든 기준을 충족해야 하기 때문에 실제로는 훨씬 적은 수이지만 각 게시물에 데이터 집합에서 최대 ('50' '2'를 선택) 주석이 있을 수 있음을 의미 합니다.\n\n\n레드딧은 서브레드딧마다 상위 1000개 이상의 게시물을 얻는 것을 매우 어렵게 만든다.\n최상위 1,000개의 게시물부터 시작하여 Reddit의 검색 기능을 사용하여 각 게시물과 가장 유사한 25개의 게시물을 검색하여 하위 레딧당 최대 7500개의 고유한 게시물 ID를 얻었다.",
"passage: ### 전처리\n\n\n전처리를 최소한으로 유지하려고 노력했습니다. 서브레디트-특정 약어는 확장되었다(예를 들어, \"CMV\"를 \"내 견해를 변경\"으로).\n하이퍼링크에서, 참조 텍스트만이 유지되고 URL이 제거되었다(URL이 기입된 경우, 그것은 유지되었다).\n\n\n기본 설정 모델 만들기\n------------",
"passage: ### Finetuning\n\n\n인간 선호도(예를 들어, NLG 평가 또는 RLHF 보상 모델에 대해)를 예측하기 위해 모델을 피니튜닝하고자 하는 경우, 여기 몇 가지 유용한 팁이 있다:\n\n\n1. 데이터를 전처리합니다.\\* \\* 총 입력 길이는 모델의 토큰 제한 (일반적으로 512 토큰)에 적합 해야 합니다.\nFLAN-T5와 같은 모델은 위치 임베딩을 사용하지만 512개 토큰 이상의 입력에서 손실을 조정하면 손실이 수렴하지 않는다는 것을 발견했다.\n이를 방지 하려면 게시글 텍스트 ('history' 필드에서)를 가능한 한 잘라서 전체 입력이 512 토큰 아래에 있도록 합니다 (그러나 주석을 잘리지 않음).\n여전히 512 토큰 이상이면 예제를 건너뜁니다.\n2. 충분히 큰 모델을 사용 합니다.\n모든 트레이닝 데이터에 걸쳐 단일 FLAN-T5-xl 모델을 피니튜닝하는 것은 72-73%(전체 입력이 토큰 한계 내에 맞는 예시의 모든 도메인에 걸쳐) 사이의 테스트 정확도를 제공해야 하며, 개별 서브레딧의 경우 65-80% 범위이다.\n3. 도메인 내 예측을 수행 합니다.\\* \\* 하위 레딧이 관련이 없는 경우 도메인 외 성능이 좋지 않습니다 (예: 환경 설정을 미세 조정 하 고 환경 설정을 테스트 하는 경우 'askculinary' 'askcarguys').\n4. 더 적은 에폭에 대해 훈련 InstructGPT 종이 페이퍼는 1 에폭에 대해서만 보상 모델을 훈련하는 것을 제안합니다.\n동일한 코멘트가 여러 선호도에서 나타나기 때문에 데이터에 과적합되기 쉽다.\n5. 더 적은 데이터에 대한 교육이 도움이 될 수 있습니다\\* \\*.\n큰 'score\\_ratio'를 사용하는 환경 설정(예: 주석 B의 점수가 2배인 주석 A)은 모델을 조정하기 위한 더 강력한 신호를 제공하므로 특정 이상의 환경 설정만 고려하려는 것일 수 있습니다 'score\\_ratio'.\n게시물당 선호도 수는 Pareto-distributed이므로 모델이 특정 게시물에 과도하게 적합 하는 것을 방지 하기 위해 특정 게시물에서 선호도 수를 제한 하는 것이 좋습니다.### 평가\n\n\n약한 기본 설정보다 강력한 기본 설정을 예측하는 것이 더 쉽기 때문에 단일 정확도 값을 보고하는 대신 성능 곡선을 'score\\_ratio'의 함수로 보고하는 것이 좋습니다.\n예를 들어, 여기 위의 제안들을 사용하여 질문적 데이터에 대해 트레이닝된 FLAN-T5-xl 모델에 대한 정확도 곡선이 있다.\n주황색 라인은 2+ 스코어 비율을 갖는 선호도에만 피니튜닝하고 과적합을 방지하기 위해 각 포스트로부터 5개 이하의 선호도를 사용하는 것이다:\n\n\n로 이루어진 군에서 선택되는 어느 하나인 것을 특징으로 하는 유기 발광 표시 장치. 그래프\n\n\n우리는 더 낮지만 더 높은 품질의 데이터를 미세 조정하는 것이 실제 단점이 없는 점수 비율이 3.5 미만인 테스트 데이터에 대한 더 높은 정확도로 이어진다는 것을 알 수 있다!\n토큰 제한 내에 입력이 맞지 않는 예는 모델에서 처리할 것으로 예상할 수 없기 때문에 실험에서 제외되었다.### SteamSHP - Open-Source Preference Model\n\n\n우리는 SHP 데이터 세트와 Anthropic의 HH-RLHF의 도움 데이터 모두에 대해 두 개의 FLAN-T5 모델을 미세 조정했다. 그들은\n\n\n* 테스트 데이터에서 72.8%를 달성하는 3B 매개 변수 모델인 SteamSHP-XL입니다.\n* 테스트 데이터에서 72.0%를 달성하는 780M 매개 변수 모델인 SteamSHP-Large입니다.\n\n\nNLG 평가, RLHF에 대한 보상 모델 구축 또는 적합하다고 생각하는 다른 목적으로 스팀SHP를 사용하는 것이 좋습니다!\n\n\n편향 및 제한 사항\n----------",
"passage: ### Biases\n\n\nNSFW(18세 이상) 콘텐츠로 게시물을 걸러내고, 잘 조정되고 괴롭힘과 편협에 대한 정책이 있는 하위 레딧을 선택했지만 일부 데이터에는 차별적이거나 해로운 언어가 포함될 수 있다.\n데이터는 데이터 세트 작성자의 보기를 반영하지 않습니다.\n이러한 하위 레딧의 레딧 사용자도 광범위한 모집단을 대표하지 않는다.\n하위 레딧별 인구 통계 정보는 사용할 수 없지만 전체 레딧 사용자는 불균형적으로 남성이며 선진국, 서양 및 영어 사용 국가에서 왔습니다 (Pew Research).\n이 데이터에 대해 학습된 모델을 사용하기 전에 이 점을 염두에 두십시오."
] |
5bab4ac27d40beb13d05c2bb170a92eb3bd72f32 |
# LMDrive 64K Dataset Card
LMDrive Dataset consists of 64K instruction-sensor-control data clips collected in the CARLA simulator， where each clip includes one navigation instruction, several notice instructions, a sequence of multi-modal multi-view sensor data, and control signals. The duration of the clip spans from 2 to 20 seconds.
## Dataset details
- `data/`: dataset folder, the entire dataset contains about 2T of data.
- `data/Town01`: sub dataset folder, which only consists of the data folder for the Town01
- `data/Town02`: sub dataset folder, which only consists of the data folder for the Town02
- ...
- `dataset_index.txt`: the data list for pretraining the vision encoder
- `navigation_instruction_list.txt`: the data list for instruction finetuning
- `notice_instruction_list.json`: the data list for instruction finetuning (optional if the notice instruction data is not engaged in the training)
**Dataset date:**
LMDrive-1.0 Dataset was collected in September 2023.
**Paper or resources for more information:**
Github: https://github.com/opendilab/LMDrive/README.md
Paper: https://arxiv.org/abs/2312.07488
**License:**
Attribution-NonCommercial 4.0 International
**Where to send questions or comments about the model:**
https://github.com/opendilab/LMDrive/issues
## Intended use
**Primary intended uses:**
The primary use of LMDrive is research on large multimodal models for autonomous driving.
**Primary intended users:**
The primary intended users of the model are researchers and hobbyists in computer vision, large multimodal model, autonomous driving, and artificial intelligence. | OpenDILabCommunity/LMDrive | [
"size_categories:n>1T",
"language:en",
"license:apache-2.0",
"arxiv:2312.07488",
"region:us"
] | 2023-11-30T08:56:30+00:00 | {"language": ["en"], "license": "apache-2.0", "size_categories": ["n>1T"], "configs": [{"config_name": "default", "data_files": [{"split": "train", "path": "navigation_instruction_list.txt"}], "sep": " ", "default": true}]} | 2023-12-25T13:28:07+00:00 | [
"2312.07488"
] | [
"en"
] | TAGS
#size_categories-n>1T #language-English #license-apache-2.0 #arxiv-2312.07488 #region-us
|
# LMDrive 64K Dataset Card
LMDrive Dataset consists of 64K instruction-sensor-control data clips collected in the CARLA simulator， where each clip includes one navigation instruction, several notice instructions, a sequence of multi-modal multi-view sensor data, and control signals. The duration of the clip spans from 2 to 20 seconds.
## Dataset details
- 'data/': dataset folder, the entire dataset contains about 2T of data.
- 'data/Town01': sub dataset folder, which only consists of the data folder for the Town01
- 'data/Town02': sub dataset folder, which only consists of the data folder for the Town02
- ...
- 'dataset_index.txt': the data list for pretraining the vision encoder
- 'navigation_instruction_list.txt': the data list for instruction finetuning
- 'notice_instruction_list.json': the data list for instruction finetuning (optional if the notice instruction data is not engaged in the training)
Dataset date:
LMDrive-1.0 Dataset was collected in September 2023.
Paper or resources for more information:
Github: URL
Paper: URL
License:
Attribution-NonCommercial 4.0 International
Where to send questions or comments about the model:
URL
## Intended use
Primary intended uses:
The primary use of LMDrive is research on large multimodal models for autonomous driving.
Primary intended users:
The primary intended users of the model are researchers and hobbyists in computer vision, large multimodal model, autonomous driving, and artificial intelligence. | [
"# LMDrive 64K Dataset Card\n\nLMDrive Dataset consists of 64K instruction-sensor-control data clips collected in the CARLA simulator， where each clip includes one navigation instruction, several notice instructions, a sequence of multi-modal multi-view sensor data, and control signals. The duration of the clip spans from 2 to 20 seconds.",
"## Dataset details\n\n- 'data/': dataset folder, the entire dataset contains about 2T of data.\n - 'data/Town01': sub dataset folder, which only consists of the data folder for the Town01\n - 'data/Town02': sub dataset folder, which only consists of the data folder for the Town02\n - ...\n- 'dataset_index.txt': the data list for pretraining the vision encoder\n- 'navigation_instruction_list.txt': the data list for instruction finetuning\n- 'notice_instruction_list.json': the data list for instruction finetuning (optional if the notice instruction data is not engaged in the training)\n\n\nDataset date:\nLMDrive-1.0 Dataset was collected in September 2023. \n\nPaper or resources for more information:\n\nGithub: URL\n\nPaper: URL\n\nLicense:\nAttribution-NonCommercial 4.0 International\n\nWhere to send questions or comments about the model:\nURL",
"## Intended use\nPrimary intended uses:\n\nThe primary use of LMDrive is research on large multimodal models for autonomous driving.\n\nPrimary intended users:\n\nThe primary intended users of the model are researchers and hobbyists in computer vision, large multimodal model, autonomous driving, and artificial intelligence."
] | [
"TAGS\n#size_categories-n>1T #language-English #license-apache-2.0 #arxiv-2312.07488 #region-us \n",
"# LMDrive 64K Dataset Card\n\nLMDrive Dataset consists of 64K instruction-sensor-control data clips collected in the CARLA simulator， where each clip includes one navigation instruction, several notice instructions, a sequence of multi-modal multi-view sensor data, and control signals. The duration of the clip spans from 2 to 20 seconds.",
"## Dataset details\n\n- 'data/': dataset folder, the entire dataset contains about 2T of data.\n - 'data/Town01': sub dataset folder, which only consists of the data folder for the Town01\n - 'data/Town02': sub dataset folder, which only consists of the data folder for the Town02\n - ...\n- 'dataset_index.txt': the data list for pretraining the vision encoder\n- 'navigation_instruction_list.txt': the data list for instruction finetuning\n- 'notice_instruction_list.json': the data list for instruction finetuning (optional if the notice instruction data is not engaged in the training)\n\n\nDataset date:\nLMDrive-1.0 Dataset was collected in September 2023. \n\nPaper or resources for more information:\n\nGithub: URL\n\nPaper: URL\n\nLicense:\nAttribution-NonCommercial 4.0 International\n\nWhere to send questions or comments about the model:\nURL",
"## Intended use\nPrimary intended uses:\n\nThe primary use of LMDrive is research on large multimodal models for autonomous driving.\n\nPrimary intended users:\n\nThe primary intended users of the model are researchers and hobbyists in computer vision, large multimodal model, autonomous driving, and artificial intelligence."
] | [
37,
84,
216,
68
] | [
"passage: TAGS\n#size_categories-n>1T #language-English #license-apache-2.0 #arxiv-2312.07488 #region-us \n# LMDrive 64K Dataset Card\n\nLMDrive Dataset consists of 64K instruction-sensor-control data clips collected in the CARLA simulator， where each clip includes one navigation instruction, several notice instructions, a sequence of multi-modal multi-view sensor data, and control signals. The duration of the clip spans from 2 to 20 seconds.## Dataset details\n\n- 'data/': dataset folder, the entire dataset contains about 2T of data.\n - 'data/Town01': sub dataset folder, which only consists of the data folder for the Town01\n - 'data/Town02': sub dataset folder, which only consists of the data folder for the Town02\n - ...\n- 'dataset_index.txt': the data list for pretraining the vision encoder\n- 'navigation_instruction_list.txt': the data list for instruction finetuning\n- 'notice_instruction_list.json': the data list for instruction finetuning (optional if the notice instruction data is not engaged in the training)\n\n\nDataset date:\nLMDrive-1.0 Dataset was collected in September 2023. \n\nPaper or resources for more information:\n\nGithub: URL\n\nPaper: URL\n\nLicense:\nAttribution-NonCommercial 4.0 International\n\nWhere to send questions or comments about the model:\nURL## Intended use\nPrimary intended uses:\n\nThe primary use of LMDrive is research on large multimodal models for autonomous driving.\n\nPrimary intended users:\n\nThe primary intended users of the model are researchers and hobbyists in computer vision, large multimodal model, autonomous driving, and artificial intelligence."
] |
7beb6a92fb2e2a8eea94b7d2d8e4cc0c34670446 | # Dataset Card for "VoiceConversion_VCTK"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | DynamicSuperb/VoiceConversion_VCTK | [
"region:us"
] | 2023-11-30T08:59:08+00:00 | {"configs": [{"config_name": "default", "data_files": [{"split": "test", "path": "data/test-*"}]}], "dataset_info": {"features": [{"name": "source_speech_id", "dtype": "string"}, {"name": "source_speech", "dtype": {"audio": {"sampling_rate": 48000}}}, {"name": "source_transcription", "dtype": "string"}, {"name": "target_speech_id", "dtype": "string"}, {"name": "target_speech", "dtype": {"audio": {"sampling_rate": 48000}}}, {"name": "target_transcription", "dtype": "string"}, {"name": "label_id", "dtype": "string"}, {"name": "label", "dtype": {"audio": {"sampling_rate": 48000}}}, {"name": "label_transcription", "dtype": "string"}, {"name": "instruction", "dtype": "string"}], "splits": [{"name": "test", "num_bytes": 3132068107.564, "num_examples": 2001}], "download_size": 2043675326, "dataset_size": 3132068107.564}} | 2023-11-30T09:02:34+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "VoiceConversion_VCTK"
More Information needed | [
"# Dataset Card for \"VoiceConversion_VCTK\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"VoiceConversion_VCTK\"\n\nMore Information needed"
] | [
6,
17
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"VoiceConversion_VCTK\"\n\nMore Information needed"
] |
236baa10495af451de38485123a90f60e7632bbd | LICENSE
You may redistribute, republish, and mirror the CSE-CIC-IDS2018 dataset in any form. However, any use or redistribution of the data must include a citation to the CSE-CIC-IDS2018 dataset and a link to this page in AWS.
Research paper outlining the details of analyzing the similar IDS/IPS dataset and related principles:
* Iman Sharafaldin, Arash Habibi Lashkari, and Ali A. Ghorbani, “Toward Generating a New Intrusion Detection Dataset and Intrusion Traffic Characterization”, 4th International Conference on Information Systems Security and Privacy (ICISSP), Portugal, January 2018 | c01dsnap/CIC-IDS2018 | [
"region:us"
] | 2023-11-30T09:22:46+00:00 | {} | 2023-12-01T01:47:45+00:00 | [] | [] | TAGS
#region-us
| LICENSE
You may redistribute, republish, and mirror the CSE-CIC-IDS2018 dataset in any form. However, any use or redistribution of the data must include a citation to the CSE-CIC-IDS2018 dataset and a link to this page in AWS.
Research paper outlining the details of analyzing the similar IDS/IPS dataset and related principles:
* Iman Sharafaldin, Arash Habibi Lashkari, and Ali A. Ghorbani, “Toward Generating a New Intrusion Detection Dataset and Intrusion Traffic Characterization”, 4th International Conference on Information Systems Security and Privacy (ICISSP), Portugal, January 2018 | [] | [
"TAGS\n#region-us \n"
] | [
6
] | [
"passage: TAGS\n#region-us \n"
] |
93a3b2a805ccd8c8e3e59c3ed91dedb9c5decead | # Dataset Card for "coref_dataset"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | gguichard/coref_dataset | [
"region:us"
] | 2023-11-30T09:24:53+00:00 | {"configs": [{"config_name": "default", "data_files": [{"split": "train", "path": "data/train-*"}, {"split": "test", "path": "data/test-*"}]}], "dataset_info": {"features": [{"name": "input_ids", "sequence": "int32"}, {"name": "labels", "sequence": "int64"}], "splits": [{"name": "train", "num_bytes": 595904106.6677296, "num_examples": 101287}, {"name": "test", "num_bytes": 31363993.332270347, "num_examples": 5331}], "download_size": 94532509, "dataset_size": 627268100.0}} | 2023-11-30T09:26:08+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "coref_dataset"
More Information needed | [
"# Dataset Card for \"coref_dataset\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"coref_dataset\"\n\nMore Information needed"
] | [
6,
15
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"coref_dataset\"\n\nMore Information needed"
] |
52a86a699bb27009e0945b14abaab84e3fb1da41 | # Dataset Card for "handling_charges_v2"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | paul-w-qs/handling_charges_v2 | [
"region:us"
] | 2023-11-30T09:54:47+00:00 | {"configs": [{"config_name": "default", "data_files": [{"split": "train", "path": "data/train-*"}]}], "dataset_info": {"features": [{"name": "image", "dtype": "image"}, {"name": "JSON_LABEL", "dtype": "string"}], "splits": [{"name": "train", "num_bytes": 493878408.0, "num_examples": 1000}], "download_size": 491831352, "dataset_size": 493878408.0}} | 2023-11-30T18:44:55+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "handling_charges_v2"
More Information needed | [
"# Dataset Card for \"handling_charges_v2\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"handling_charges_v2\"\n\nMore Information needed"
] | [
6,
17
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"handling_charges_v2\"\n\nMore Information needed"
] |
53437fed96158d97834b3e06ef43185b8f229b23 |
원본 데이터셋: [Open-Orca/SlimOrca](https://huggingface.co/datasets/Open-Orca/SlimOrca) | nlp-with-deeplearning/Ko.SlimOrca | [
"task_categories:conversational",
"task_categories:text-classification",
"task_categories:token-classification",
"task_categories:table-question-answering",
"task_categories:question-answering",
"task_categories:zero-shot-classification",
"task_categories:summarization",
"task_categories:feature-extraction",
"task_categories:text-generation",
"task_categories:text2text-generation",
"size_categories:100K<n<1M",
"language:en",
"language:ko",
"license:cc-by-nc-sa-4.0",
"region:us"
] | 2023-11-30T09:57:45+00:00 | {"language": ["en", "ko"], "license": "cc-by-nc-sa-4.0", "size_categories": ["100K<n<1M"], "task_categories": ["conversational", "text-classification", "token-classification", "table-question-answering", "question-answering", "zero-shot-classification", "summarization", "feature-extraction", "text-generation", "text2text-generation"]} | 2023-12-04T03:29:35+00:00 | [] | [
"en",
"ko"
] | TAGS
#task_categories-conversational #task_categories-text-classification #task_categories-token-classification #task_categories-table-question-answering #task_categories-question-answering #task_categories-zero-shot-classification #task_categories-summarization #task_categories-feature-extraction #task_categories-text-generation #task_categories-text2text-generation #size_categories-100K<n<1M #language-English #language-Korean #license-cc-by-nc-sa-4.0 #region-us
|
원본 데이터셋: Open-Orca/SlimOrca | [] | [
"TAGS\n#task_categories-conversational #task_categories-text-classification #task_categories-token-classification #task_categories-table-question-answering #task_categories-question-answering #task_categories-zero-shot-classification #task_categories-summarization #task_categories-feature-extraction #task_categories-text-generation #task_categories-text2text-generation #size_categories-100K<n<1M #language-English #language-Korean #license-cc-by-nc-sa-4.0 #region-us \n"
] | [
158
] | [
"passage: TAGS\n#task_categories-conversational #task_categories-text-classification #task_categories-token-classification #task_categories-table-question-answering #task_categories-question-answering #task_categories-zero-shot-classification #task_categories-summarization #task_categories-feature-extraction #task_categories-text-generation #task_categories-text2text-generation #size_categories-100K<n<1M #language-English #language-Korean #license-cc-by-nc-sa-4.0 #region-us \n"
] |
de19f7eaa31de073fa784d240efc93c131ebca8f |
이 데이터셋은 자체 구축한 번역기로 [WizardLM/WizardLM_evol_instruct_V2_196k](https://huggingface.co/datasets/WizardLM/WizardLM_evol_instruct_V2_196k)을 번역한 데이터셋입니다. 아래 README 페이지도 번역기를 통해 번역되었습니다. 참고 부탁드립니다.
## News
- 🔥 🔥 🔥 [08/11/2023] **WizardMath** 모델을 출시합니다.
- 🔥 **WizardMath-70B-V1.0** 모델은 **ChatGPT 3.5**, **Claude Instant 1** 및 **PaLM 2 540B** 를 포함 하 여 GSM8K에서 일부 폐쇄 소스 LLMs 보다 약간 더 우수 합니다.
- 🔥 우리의 **WizardMath-70B-V1.0** 모델은 SOTA 오픈 소스 LLM보다 **24.8** 포인트 높은 [GSM8k Benchmarks](https://github.com/openai/grade-school-math)에서 **81.6 pass@1** 을 달성합니다.
- 🔥 우리의 **WizardMath-70B-V1.0** 모델은 SOTA 오픈 소스 LLM보다 **9.2** 포인트 높은 [MATH 벤치마크](https://github.com/hendrycks/math)에서 **22.7 pass@1** 을 달성합니다.
| 모델 | 체크포인트 | 용지 | GSM8k | MATH |온라인 데모| 라이선스
| ----- |------| ---- |------|-------| ----- | ----- |
| WizardMath-70B-V1.0 | 🤗 <a href="https://huggingface.co/WizardLM/WizardMath-70B-V1.0" target="_blank">HF Link</a> | 📃 <a href="https://arxiv.org/abs/2308.09583" target="_blank">[WizardMath]</a>| **81.6** | **22.7** smells|[Demo](http://47.103.63.15:50083/)| <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama 2 </a> |
| WizardMath-13B-V1.0 | 🤗 <a href="https://huggingface.co/WizardLM/WizardMath-13B-V1.0" target="_blank">HF Link</a> | 📃 <a href="https://arxiv.org/abs/2308.09583" target="_blank">[WizardMath]</a>| **63.9** | **14.0** |[Demo](http://47.103.63.15:50082/)| <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama 2</a> |
| WizardMath-7B-V1.0 | 🤗 <a href="https://huggingface.co/WizardLM/WizardMath-7B-V1.0" target="_blank">HF Link</a> | 📃 <a href="https://arxiv.org/abs/2308.09583" target="_blank">[WizardMath]</a>| Automation **54.9** | **10.7** | [Demo](http://47.103.63.15:50080/)| <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama 2 </a>|
<font size=4>
| <sup>Model</sup> | <sup>Checkpoint</sup> | <sup>Paper</sup> |<sup>MT-Bench</sup> | <sup>AlpacaEval</sup> | <sup>WizardEval</sup> | <sup>HumanEval</sup> | <sup>License</sup>|
| ----- |------| ---- |------|-------| ----- | ----- | ----- |
| <sup>WizardLM-13B-V1.2</sup> | <sup>🤗 <a href="https://huggingface.co/WizardLM/WizardLM-13B-V1.2" target="_blank">HF Link</a></sup>| | <sup>7.06</sup> | <sup>89.17%</sup>Placement | <sup>101.4%</sup>|<sup>36.6 pass@1</sup>|<sup> <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama 2 License</a></sup> |
| <sup>WizardLM-13B-V1.1</sup> |<sup> 🤗 <a href="https://huggingface.co/WizardLM/WizardLM-13B-V1.1" target="_blank">HF Link</a> </sup> | | <sup>6.76</sup> |<sup>86.32%</sup>Automation | <sup>99.3%</sup> |<sup>25.0 pass@1</sup>| <sup>Noncommercial</sup>|
| <sup>WizardLM-30B-V1.0</sup> | <sup>🤗 <a href="https://huggingface.co/WizardLM/WizardLM-30B-V1.0" target="_blank">HF Link</a></sup> | | <sup>7.01</sup> | | <sup>97.8%</sup> | <sup>37.8 pass@1</sup>| <sup>비상업</sup> |
| <sup>WizardLM-13B-V1.0</sup> | <sup>🤗 <a href="https://huggingface.co/WizardLM/WizardLM-13B-V1.0" target="_blank">HF Link</a></sup> | | <sup>6.35</sup> | <sup>75.31%</sup> | <sup>89.1%</sup> | <sup>24.0 pass@1</sup> | <sup>비상업</sup>|
| <sup>WizardLM-7B-V1.0</sup>| <sup>🤗 <a href="https://huggingface.co/WizardLM/WizardLM-7B-V1.0" target="_blank">HF Link</a></sup> |<sup> 📃 <a href="https://arxiv.org/abs/2304.12244" target="_blank">[WizardLM]</a></sup>| | | <sup>78.0%</sup> |<sup>19.1 pass@1</sup>|<sup> 비상업적</sup>|
| <sup>WizardCoder-15B-V1.0</sup> | <sup> 🤗 <a href="https://huggingface.co/WizardLM/WizardCoder-15B-V1.0" target="_blank">HF Link</a></sup> | <sup>📃 <a href="https://arxiv.org/abs/2306.08568" target="_blank">[WizardCoder]</a></sup> | || <sup> 57.3 pass@1</sup> | <sup> <a href="https://huggingface.co/spaces/bigcode/bigcode-model-license-agreement" target="_blank">OpenRAIL-M</a></sup> |
</font>
**리포지토리**: https://github.com/nlpxucan/WizardLM
**Twitter**: https://twitter.com/WizardLM_AI/status/1669364947606982656
이 데이터 세트에는 알파카와 샤레GPT의 143K 혼합 진화 데이터가 포함되어 있다.
이것은 WizardLM 모델의 Evol-Instruct 학습 데이터의 최신 최적화 버전이다.
데이터 사용 라이선스로 인해 약 196k 데이터 행으로 구성된 **최종 전체 데이터 세트** 를 가져오려면 원본 [ShareGPT](https://huggingface.co/datasets/anon8231489123/ShareGPT_Vicuna_unfiltered)를 **병합**하십시오. | nlp-with-deeplearning/Ko.WizardLM_evol_instruct_V2_196k | [
"task_categories:text-generation",
"task_categories:question-answering",
"language:en",
"language:ko",
"license:cc-by-nc-sa-4.0",
"arxiv:2308.09583",
"arxiv:2304.12244",
"arxiv:2306.08568",
"region:us"
] | 2023-11-30T10:00:05+00:00 | {"language": ["en", "ko"], "license": "cc-by-nc-sa-4.0", "task_categories": ["text-generation", "question-answering"]} | 2023-12-01T01:42:39+00:00 | [
"2308.09583",
"2304.12244",
"2306.08568"
] | [
"en",
"ko"
] | TAGS
#task_categories-text-generation #task_categories-question-answering #language-English #language-Korean #license-cc-by-nc-sa-4.0 #arxiv-2308.09583 #arxiv-2304.12244 #arxiv-2306.08568 #region-us
| 이 데이터셋은 자체 구축한 번역기로 WizardLM/WizardLM\_evol\_instruct\_V2\_196k을 번역한 데이터셋입니다. 아래 README 페이지도 번역기를 통해 번역되었습니다. 참고 부탁드립니다.
News
----
* [08/11/2023] WizardMath 모델을 출시합니다.
* WizardMath-70B-V1.0 모델은 ChatGPT 3.5, Claude Instant 1 및 PaLM 2 540B 를 포함 하 여 GSM8K에서 일부 폐쇄 소스 LLMs 보다 약간 더 우수 합니다.
* 우리의 WizardMath-70B-V1.0 모델은 SOTA 오픈 소스 LLM보다 24.8 포인트 높은 GSM8k Benchmarks에서 81.6 pass@1 을 달성합니다.
* 우리의 WizardMath-70B-V1.0 모델은 SOTA 오픈 소스 LLM보다 9.2 포인트 높은 MATH 벤치마크에서 22.7 pass@1 을 달성합니다.
리포지토리: URL
Twitter: URL
이 데이터 세트에는 알파카와 샤레GPT의 143K 혼합 진화 데이터가 포함되어 있다.
이것은 WizardLM 모델의 Evol-Instruct 학습 데이터의 최신 최적화 버전이다.
데이터 사용 라이선스로 인해 약 196k 데이터 행으로 구성된 최종 전체 데이터 세트 를 가져오려면 원본 ShareGPT를 병합하십시오.
| [] | [
"TAGS\n#task_categories-text-generation #task_categories-question-answering #language-English #language-Korean #license-cc-by-nc-sa-4.0 #arxiv-2308.09583 #arxiv-2304.12244 #arxiv-2306.08568 #region-us \n"
] | [
76
] | [
"passage: TAGS\n#task_categories-text-generation #task_categories-question-answering #language-English #language-Korean #license-cc-by-nc-sa-4.0 #arxiv-2308.09583 #arxiv-2304.12244 #arxiv-2306.08568 #region-us \n"
] |
83ceca0adf517a12eb65a591d8832dafcab4eca0 | #### Overview
The 8chan initiative emanates from the Sleeping AI Lab, aiming to furnish the research community with a superlative dataset in unconventional domains. Aligned with Sleeping AI's Datasets initiative, our commitment is directed toward furnishing premium Open Source datasets, with 8chan standing out as a singular endeavour that delves into a segment of the Internet colloquially known as the Dark Web, often deemed taboo in mainstream media.
Our contribution encompasses media and image data extracted from the 8chan image board, serving as the enigmatic counterpart to the 4chan platform. This pioneering dataset distinguishes itself within the research community, being the inaugural compilation exclusively dedicated to 8chan. We trust that the community will exercise due responsibility in its utilisation.
#### Technical Aspects of the Dataset
Within this dataset, designated as **kun** vartaint, individuals may discover unaltered media and images sourced from the entirety of the 8chan platform, encompassing all 488 boards and their respective threads up until November 30, 2023. Subsequently, these data were downloaded and stored within the overarching super-folder 'kun,' with each board's collected data residing in its distinct folder identified by the nomenclature "board = foldername."
Metadata pertaining to the uploaded user accompanies the media, inclusive of sensitive information. Accordingly, we implore researchers to employ this information ethically and responsibly. Despite the presence of numerous corrupted images and media, their discerning examination reveals commensurate value.
For practical engagement with the images, an image-specific subset of the scraped data embedding has been disseminated on Kaggle, fostering the development of robust and innovative models.
Subsequently, we introduced a refined variant, **clear_kun**, representing a preprocessed and sanitised iteration of the dataset. This version, comprising 3882 images, has undergone meticulous filtering to eliminate corruptions and serves as the foundation for generating embeddings.
#### Liability
It is imperative to clarify that any potential misuse by third parties absolves the undersigned of responsibility. We uphold a stringent request policy, necessitating interested parties to submit requests for dataset access, which will be individually reviewed. Researchers are strongly encouraged to uphold privacy and adhere to ethical guidelines, with any inadvertent misuse falling outside the purview of responsibility.
The release of this dataset is expressly intended for academic and research purposes, encompassing content should be viewed by 20 and above older individuals.
For inquiries or concerns, please direct correspondence to *[email protected].*
Kaggle (Image Embedding): https://www.kaggle.com/datasets/sleepingcat4/8chan-image-embeddings/data | sleeping4cat/8chan | [
"language:en",
"license:bigscience-openrail-m",
"doi:10.57967/hf/1411",
"region:us"
] | 2023-11-30T10:05:14+00:00 | {"language": ["en"], "license": "bigscience-openrail-m", "pretty_name": "scarlet-dark"} | 2023-11-30T21:19:45+00:00 | [] | [
"en"
] | TAGS
#language-English #license-bigscience-openrail-m #doi-10.57967/hf/1411 #region-us
| #### Overview
The 8chan initiative emanates from the Sleeping AI Lab, aiming to furnish the research community with a superlative dataset in unconventional domains. Aligned with Sleeping AI's Datasets initiative, our commitment is directed toward furnishing premium Open Source datasets, with 8chan standing out as a singular endeavour that delves into a segment of the Internet colloquially known as the Dark Web, often deemed taboo in mainstream media.
Our contribution encompasses media and image data extracted from the 8chan image board, serving as the enigmatic counterpart to the 4chan platform. This pioneering dataset distinguishes itself within the research community, being the inaugural compilation exclusively dedicated to 8chan. We trust that the community will exercise due responsibility in its utilisation.
#### Technical Aspects of the Dataset
Within this dataset, designated as kun vartaint, individuals may discover unaltered media and images sourced from the entirety of the 8chan platform, encompassing all 488 boards and their respective threads up until November 30, 2023. Subsequently, these data were downloaded and stored within the overarching super-folder 'kun,' with each board's collected data residing in its distinct folder identified by the nomenclature "board = foldername."
Metadata pertaining to the uploaded user accompanies the media, inclusive of sensitive information. Accordingly, we implore researchers to employ this information ethically and responsibly. Despite the presence of numerous corrupted images and media, their discerning examination reveals commensurate value.
For practical engagement with the images, an image-specific subset of the scraped data embedding has been disseminated on Kaggle, fostering the development of robust and innovative models.
Subsequently, we introduced a refined variant, clear_kun, representing a preprocessed and sanitised iteration of the dataset. This version, comprising 3882 images, has undergone meticulous filtering to eliminate corruptions and serves as the foundation for generating embeddings.
#### Liability
It is imperative to clarify that any potential misuse by third parties absolves the undersigned of responsibility. We uphold a stringent request policy, necessitating interested parties to submit requests for dataset access, which will be individually reviewed. Researchers are strongly encouraged to uphold privacy and adhere to ethical guidelines, with any inadvertent misuse falling outside the purview of responsibility.
The release of this dataset is expressly intended for academic and research purposes, encompassing content should be viewed by 20 and above older individuals.
For inquiries or concerns, please direct correspondence to *sleeping4cat@URL.*
Kaggle (Image Embedding): URL | [
"#### Overview\n\n\nThe 8chan initiative emanates from the Sleeping AI Lab, aiming to furnish the research community with a superlative dataset in unconventional domains. Aligned with Sleeping AI's Datasets initiative, our commitment is directed toward furnishing premium Open Source datasets, with 8chan standing out as a singular endeavour that delves into a segment of the Internet colloquially known as the Dark Web, often deemed taboo in mainstream media.\nOur contribution encompasses media and image data extracted from the 8chan image board, serving as the enigmatic counterpart to the 4chan platform. This pioneering dataset distinguishes itself within the research community, being the inaugural compilation exclusively dedicated to 8chan. We trust that the community will exercise due responsibility in its utilisation.",
"#### Technical Aspects of the Dataset\nWithin this dataset, designated as kun vartaint, individuals may discover unaltered media and images sourced from the entirety of the 8chan platform, encompassing all 488 boards and their respective threads up until November 30, 2023. Subsequently, these data were downloaded and stored within the overarching super-folder 'kun,' with each board's collected data residing in its distinct folder identified by the nomenclature \"board = foldername.\"\nMetadata pertaining to the uploaded user accompanies the media, inclusive of sensitive information. Accordingly, we implore researchers to employ this information ethically and responsibly. Despite the presence of numerous corrupted images and media, their discerning examination reveals commensurate value.\nFor practical engagement with the images, an image-specific subset of the scraped data embedding has been disseminated on Kaggle, fostering the development of robust and innovative models.\nSubsequently, we introduced a refined variant, clear_kun, representing a preprocessed and sanitised iteration of the dataset. This version, comprising 3882 images, has undergone meticulous filtering to eliminate corruptions and serves as the foundation for generating embeddings.",
"#### Liability\nIt is imperative to clarify that any potential misuse by third parties absolves the undersigned of responsibility. We uphold a stringent request policy, necessitating interested parties to submit requests for dataset access, which will be individually reviewed. Researchers are strongly encouraged to uphold privacy and adhere to ethical guidelines, with any inadvertent misuse falling outside the purview of responsibility.\nThe release of this dataset is expressly intended for academic and research purposes, encompassing content should be viewed by 20 and above older individuals. \nFor inquiries or concerns, please direct correspondence to *sleeping4cat@URL.*\n\nKaggle (Image Embedding): URL"
] | [
"TAGS\n#language-English #license-bigscience-openrail-m #doi-10.57967/hf/1411 #region-us \n",
"#### Overview\n\n\nThe 8chan initiative emanates from the Sleeping AI Lab, aiming to furnish the research community with a superlative dataset in unconventional domains. Aligned with Sleeping AI's Datasets initiative, our commitment is directed toward furnishing premium Open Source datasets, with 8chan standing out as a singular endeavour that delves into a segment of the Internet colloquially known as the Dark Web, often deemed taboo in mainstream media.\nOur contribution encompasses media and image data extracted from the 8chan image board, serving as the enigmatic counterpart to the 4chan platform. This pioneering dataset distinguishes itself within the research community, being the inaugural compilation exclusively dedicated to 8chan. We trust that the community will exercise due responsibility in its utilisation.",
"#### Technical Aspects of the Dataset\nWithin this dataset, designated as kun vartaint, individuals may discover unaltered media and images sourced from the entirety of the 8chan platform, encompassing all 488 boards and their respective threads up until November 30, 2023. Subsequently, these data were downloaded and stored within the overarching super-folder 'kun,' with each board's collected data residing in its distinct folder identified by the nomenclature \"board = foldername.\"\nMetadata pertaining to the uploaded user accompanies the media, inclusive of sensitive information. Accordingly, we implore researchers to employ this information ethically and responsibly. Despite the presence of numerous corrupted images and media, their discerning examination reveals commensurate value.\nFor practical engagement with the images, an image-specific subset of the scraped data embedding has been disseminated on Kaggle, fostering the development of robust and innovative models.\nSubsequently, we introduced a refined variant, clear_kun, representing a preprocessed and sanitised iteration of the dataset. This version, comprising 3882 images, has undergone meticulous filtering to eliminate corruptions and serves as the foundation for generating embeddings.",
"#### Liability\nIt is imperative to clarify that any potential misuse by third parties absolves the undersigned of responsibility. We uphold a stringent request policy, necessitating interested parties to submit requests for dataset access, which will be individually reviewed. Researchers are strongly encouraged to uphold privacy and adhere to ethical guidelines, with any inadvertent misuse falling outside the purview of responsibility.\nThe release of this dataset is expressly intended for academic and research purposes, encompassing content should be viewed by 20 and above older individuals. \nFor inquiries or concerns, please direct correspondence to *sleeping4cat@URL.*\n\nKaggle (Image Embedding): URL"
] | [
33,
181,
302,
159
] | [
"passage: TAGS\n#language-English #license-bigscience-openrail-m #doi-10.57967/hf/1411 #region-us \n#### Overview\n\n\nThe 8chan initiative emanates from the Sleeping AI Lab, aiming to furnish the research community with a superlative dataset in unconventional domains. Aligned with Sleeping AI's Datasets initiative, our commitment is directed toward furnishing premium Open Source datasets, with 8chan standing out as a singular endeavour that delves into a segment of the Internet colloquially known as the Dark Web, often deemed taboo in mainstream media.\nOur contribution encompasses media and image data extracted from the 8chan image board, serving as the enigmatic counterpart to the 4chan platform. This pioneering dataset distinguishes itself within the research community, being the inaugural compilation exclusively dedicated to 8chan. We trust that the community will exercise due responsibility in its utilisation."
] |
c3cc887c1d1adcca66f5cb44f35540abcb511648 |
# Deep Dungeons and Dragons
A dataset of long-form multi-turn and multi-character collaborative RPG stories, complete with associated character cards.
This dataset comprises of 56,000 turns in 1544 stories following 9771 characters: a total of **50M Llama tokens**.
Each turn comprises a multi-paragraph continuation of a story from the perspective of a defined character including both dialogue and prose.
This dataset is a cleaned and reformatted version of [Deep Dungeons and Dragons](https://groups.inf.ed.ac.uk/cup/ddd/), originally released in 2018 by Annie Louis and Charles Sutton and comprising of transcripts collected from public games at [roleplayerguild.com](https://roleplayerguild.com). We've removed images and links (as well as their references) from posts to make this a text-only dataset, as well as anonymising usernames - although this is still available in the original dataset.
**Citation for source dataset:**
```
@inproceedings{ddd2018,
author={Louis, Annie, and Sutton, Charles},
title={{Deep Dungeons and Dragons: Learning Character-Action Interactions from Role-Playing Game Transcripts}},
booktitle={The 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies},
year={2018},
pages={--},
organization={ACL}
}
```
### Schema
- **thread_id:** The numeric ID of a specific RPG game.
- **message_id:** The turn within a thread.
- **author_id:** ID corresponding to the message author.
- **author_num_posts:** The total number of posts by that author - may be usable as a quality signal.
- **message:** The post containing a continuation of the RPG story roleplaying as a specific character. Most of the time, this is a multi-paragraph description containing both prose and dialogue.
- **character:** The character card that this post is role-playing as. This is 1-to-1 mapped to (thread_id, author_id).
### Example post
```
Trevor's abrupt announcement did, in fact, startle Mildred. The normal type jumped in just the wrong direction, toppling her mug and sending a spreading puddle of Pechai tea all over her desk. Mildred stared in shock for just a moment. Then she let out a yelp and shoved her papers to the side with speed to rival a Jolteon, saving all but a few corners from certain doom. The secretary then soaked up some of the mess with the first semi-absorbent material she could find...her own tail.
Crisis averted, Mildred suddenly remembered its cause and blushed red. She peeked up at the potential recruits, one a Noibat and the other... a Togepi? Yes, it fit the description she read, though she had never seen one in the flesh before. And now they had both seen her freak out like an idiot. Mildred took a calming breath. Time to be professional. And, in the flustered pokemon's attempt at logic, that meant acting like nothing happened. Mildred cleared her throat and plastered on a polite smile.
"Welcome to the Medburn Exploration Guild." Mildred began her standard spiel while slowly sliding her tea-stained tail behind her back. "Thank you for your interest in helping us protect the people, places, and culture of our region. My name is Mildred, and I will register you and begin your orientation today. But before we can begin, there are just a few forms I'll need you to read fully and fill out."
With that, Mildred quickly leafed through the slightly disheveled stack of colored papers. As she did so, she quickly summarized each form by memory.
"...percent of your earnings will go to the guild..."
"...will be lodged in separate..."
"...may only sing in the shower on Fridays..."
"...will not be held responsible for any injury or death caused by..."
Finally, Mildred picked up a stack of forms that looked like it belonged to a bureaucracy run by unicorns and handed it to the Togepi, since she figured the Noibat might need his arms free to fly.
"Again, I ask you to please read these thoroughly before signing anything," the Smeargle concluded, pushing her glasses up the bridge of her nose. "And feel free to ask me any questions you may have." She really hoped they wouldn't have any questions, though. She had already had enough embarrassing social situations for one day.
```
### Example character card
```
Name: Edward "Edge" Van Helsing
Appearance:
Gender: Male
Age: 15
Type: Descendant
School: Monster Hunter
Magic/Weapon(s): Mercy and Paragon
Bio: The Helsing line is one of misfortune and trouble. Edward's mother died giving birth to him, his father was a seasoned hunter. They lived in London until Edward turned nine, when disaster struck his family again. A cult of vampires gathered and assaulted the Helsing manor, a young Edward awoke to his the manor servants screaming as they vampire feasted upon them. Edge's father was surrounded gunning down each as they approached. Edge himself had collected one of the silver swords from the manors great hall. Then made his way to the window looking for his father, as the house caught fire.
Edge arrived in time to see his father drained of life, and discarded. Edge had never had drive to be violent, not until that day. In truth no Helsing is born a Hunter, nearly all of them suffer and that vengeance that burns in their hearts, that is what makes a Helsing fight. When this near year old child, with only a sword in hand saw the death of not only of his father but also of his friends and caretakers he broke. He jumped out the window crashing down upon the vampire he struck it blow after blow after blow. When his arms gave out he dropped the sword.
Luckily for Edge some of the staff had survived, now the heir of his branch of the Helsing family Edge spent days training. He also took up music, the violin specifically. It had been his mothers, now with both his parents gone he did his best to remember and learn things about them. Finally after training for years he was accepted into the Academy, choosing to train in Monster Hunting due to the fact he felt Vampire hunting would present little challenge. While tough and cocky at times, Edge backs this up with lethal aim and fast paced movement, his sword and knives skills are impressive however he knows little of magic or demons.
``` | IconicAI/DDD | [
"task_categories:text-generation",
"task_categories:conversational",
"region:us"
] | 2023-11-30T10:10:21+00:00 | {"task_categories": ["text-generation", "conversational"], "pretty_name": "Deep Dungeons and Dragons", "configs": [{"config_name": "default", "data_files": [{"split": "train", "path": "data.parquet"}]}]} | 2023-11-30T19:57:56+00:00 | [] | [] | TAGS
#task_categories-text-generation #task_categories-conversational #region-us
|
# Deep Dungeons and Dragons
A dataset of long-form multi-turn and multi-character collaborative RPG stories, complete with associated character cards.
This dataset comprises of 56,000 turns in 1544 stories following 9771 characters: a total of 50M Llama tokens.
Each turn comprises a multi-paragraph continuation of a story from the perspective of a defined character including both dialogue and prose.
This dataset is a cleaned and reformatted version of Deep Dungeons and Dragons, originally released in 2018 by Annie Louis and Charles Sutton and comprising of transcripts collected from public games at URL. We've removed images and links (as well as their references) from posts to make this a text-only dataset, as well as anonymising usernames - although this is still available in the original dataset.
Citation for source dataset:
### Schema
- thread_id: The numeric ID of a specific RPG game.
- message_id: The turn within a thread.
- author_id: ID corresponding to the message author.
- author_num_posts: The total number of posts by that author - may be usable as a quality signal.
- message: The post containing a continuation of the RPG story roleplaying as a specific character. Most of the time, this is a multi-paragraph description containing both prose and dialogue.
- character: The character card that this post is role-playing as. This is 1-to-1 mapped to (thread_id, author_id).
### Example post
### Example character card
| [
"# Deep Dungeons and Dragons\n\nA dataset of long-form multi-turn and multi-character collaborative RPG stories, complete with associated character cards.\n\nThis dataset comprises of 56,000 turns in 1544 stories following 9771 characters: a total of 50M Llama tokens. \nEach turn comprises a multi-paragraph continuation of a story from the perspective of a defined character including both dialogue and prose.\n\nThis dataset is a cleaned and reformatted version of Deep Dungeons and Dragons, originally released in 2018 by Annie Louis and Charles Sutton and comprising of transcripts collected from public games at URL. We've removed images and links (as well as their references) from posts to make this a text-only dataset, as well as anonymising usernames - although this is still available in the original dataset.\n\nCitation for source dataset:",
"### Schema\n\n- thread_id: The numeric ID of a specific RPG game.\n- message_id: The turn within a thread. \n- author_id: ID corresponding to the message author.\n- author_num_posts: The total number of posts by that author - may be usable as a quality signal.\n- message: The post containing a continuation of the RPG story roleplaying as a specific character. Most of the time, this is a multi-paragraph description containing both prose and dialogue.\n- character: The character card that this post is role-playing as. This is 1-to-1 mapped to (thread_id, author_id).",
"### Example post",
"### Example character card"
] | [
"TAGS\n#task_categories-text-generation #task_categories-conversational #region-us \n",
"# Deep Dungeons and Dragons\n\nA dataset of long-form multi-turn and multi-character collaborative RPG stories, complete with associated character cards.\n\nThis dataset comprises of 56,000 turns in 1544 stories following 9771 characters: a total of 50M Llama tokens. \nEach turn comprises a multi-paragraph continuation of a story from the perspective of a defined character including both dialogue and prose.\n\nThis dataset is a cleaned and reformatted version of Deep Dungeons and Dragons, originally released in 2018 by Annie Louis and Charles Sutton and comprising of transcripts collected from public games at URL. We've removed images and links (as well as their references) from posts to make this a text-only dataset, as well as anonymising usernames - although this is still available in the original dataset.\n\nCitation for source dataset:",
"### Schema\n\n- thread_id: The numeric ID of a specific RPG game.\n- message_id: The turn within a thread. \n- author_id: ID corresponding to the message author.\n- author_num_posts: The total number of posts by that author - may be usable as a quality signal.\n- message: The post containing a continuation of the RPG story roleplaying as a specific character. Most of the time, this is a multi-paragraph description containing both prose and dialogue.\n- character: The character card that this post is role-playing as. This is 1-to-1 mapped to (thread_id, author_id).",
"### Example post",
"### Example character card"
] | [
27,
196,
145,
5,
6
] | [
"passage: TAGS\n#task_categories-text-generation #task_categories-conversational #region-us \n# Deep Dungeons and Dragons\n\nA dataset of long-form multi-turn and multi-character collaborative RPG stories, complete with associated character cards.\n\nThis dataset comprises of 56,000 turns in 1544 stories following 9771 characters: a total of 50M Llama tokens. \nEach turn comprises a multi-paragraph continuation of a story from the perspective of a defined character including both dialogue and prose.\n\nThis dataset is a cleaned and reformatted version of Deep Dungeons and Dragons, originally released in 2018 by Annie Louis and Charles Sutton and comprising of transcripts collected from public games at URL. We've removed images and links (as well as their references) from posts to make this a text-only dataset, as well as anonymising usernames - although this is still available in the original dataset.\n\nCitation for source dataset:### Schema\n\n- thread_id: The numeric ID of a specific RPG game.\n- message_id: The turn within a thread. \n- author_id: ID corresponding to the message author.\n- author_num_posts: The total number of posts by that author - may be usable as a quality signal.\n- message: The post containing a continuation of the RPG story roleplaying as a specific character. Most of the time, this is a multi-paragraph description containing both prose and dialogue.\n- character: The character card that this post is role-playing as. This is 1-to-1 mapped to (thread_id, author_id).### Example post### Example character card"
] |
95738b3955df8ad016897d9ab8feafe60d80458a |
# Bangumi Image Base of Deatte 5-byou De Battle
This is the image base of bangumi Deatte 5-byou de Battle, we detected 30 characters, 2195 images in total. The full dataset is [here](all.zip).
**Please note that these image bases are not guaranteed to be 100% cleaned, they may be noisy actual.** If you intend to manually train models using this dataset, we recommend performing necessary preprocessing on the downloaded dataset to eliminate potential noisy samples (approximately 1% probability).
Here is the characters' preview:
| # | Images | Download | Preview 1 | Preview 2 | Preview 3 | Preview 4 | Preview 5 | Preview 6 | Preview 7 | Preview 8 |
|:------|---------:|:---------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|
| 0 | 143 | [Download](0/dataset.zip) |  |  |  |  |  |  |  |  |
| 1 | 94 | [Download](1/dataset.zip) |  |  |  |  |  |  |  |  |
| 2 | 34 | [Download](2/dataset.zip) |  |  |  |  |  |  |  |  |
| 3 | 24 | [Download](3/dataset.zip) |  |  |  |  |  |  |  |  |
| 4 | 127 | [Download](4/dataset.zip) |  |  |  |  |  |  |  |  |
| 5 | 34 | [Download](5/dataset.zip) |  |  |  |  |  |  |  |  |
| 6 | 29 | [Download](6/dataset.zip) |  |  |  |  |  |  |  |  |
| 7 | 22 | [Download](7/dataset.zip) |  |  |  |  |  |  |  |  |
| 8 | 68 | [Download](8/dataset.zip) |  |  |  |  |  |  |  |  |
| 9 | 81 | [Download](9/dataset.zip) |  |  |  |  |  |  |  |  |
| 10 | 42 | [Download](10/dataset.zip) |  |  |  |  |  |  |  |  |
| 11 | 12 | [Download](11/dataset.zip) |  |  |  |  |  |  |  |  |
| 12 | 61 | [Download](12/dataset.zip) |  |  |  |  |  |  |  |  |
| 13 | 127 | [Download](13/dataset.zip) |  |  |  |  |  |  |  |  |
| 14 | 67 | [Download](14/dataset.zip) |  |  |  |  |  |  |  |  |
| 15 | 10 | [Download](15/dataset.zip) |  |  |  |  |  |  |  |  |
| 16 | 25 | [Download](16/dataset.zip) |  |  |  |  |  |  |  |  |
| 17 | 12 | [Download](17/dataset.zip) |  |  |  |  |  |  |  |  |
| 18 | 105 | [Download](18/dataset.zip) |  |  |  |  |  |  |  |  |
| 19 | 52 | [Download](19/dataset.zip) |  |  |  |  |  |  |  |  |
| 20 | 5 | [Download](20/dataset.zip) |  |  |  |  |  | N/A | N/A | N/A |
| 21 | 74 | [Download](21/dataset.zip) |  |  |  |  |  |  |  |  |
| 22 | 27 | [Download](22/dataset.zip) |  |  |  |  |  |  |  |  |
| 23 | 20 | [Download](23/dataset.zip) |  |  |  |  |  |  |  |  |
| 24 | 7 | [Download](24/dataset.zip) |  |  |  |  |  |  |  | N/A |
| 25 | 297 | [Download](25/dataset.zip) |  |  |  |  |  |  |  |  |
| 26 | 7 | [Download](26/dataset.zip) |  |  |  |  |  |  |  | N/A |
| 27 | 17 | [Download](27/dataset.zip) |  |  |  |  |  |  |  |  |
| 28 | 27 | [Download](28/dataset.zip) |  |  |  |  |  |  |  |  |
| noise | 545 | [Download](-1/dataset.zip) |  |  |  |  |  |  |  |  |
| BangumiBase/deatte5byoudebattle | [
"size_categories:1K<n<10K",
"license:mit",
"art",
"region:us"
] | 2023-11-30T10:10:28+00:00 | {"license": "mit", "size_categories": ["1K<n<10K"], "tags": ["art"]} | 2023-11-30T11:39:24+00:00 | [] | [] | TAGS
#size_categories-1K<n<10K #license-mit #art #region-us
| Bangumi Image Base of Deatte 5-byou De Battle
=============================================
This is the image base of bangumi Deatte 5-byou de Battle, we detected 30 characters, 2195 images in total. The full dataset is here.
Please note that these image bases are not guaranteed to be 100% cleaned, they may be noisy actual. If you intend to manually train models using this dataset, we recommend performing necessary preprocessing on the downloaded dataset to eliminate potential noisy samples (approximately 1% probability).
Here is the characters' preview:
| [] | [
"TAGS\n#size_categories-1K<n<10K #license-mit #art #region-us \n"
] | [
25
] | [
"passage: TAGS\n#size_categories-1K<n<10K #license-mit #art #region-us \n"
] |
c9bdf50bcf9ad44ae89cc36626b23fc2a6230f22 |
# Bangumi Image Base of Angel Beats!
This is the image base of bangumi Angel Beats!, we detected 24 characters, 1932 images in total. The full dataset is [here](all.zip).
**Please note that these image bases are not guaranteed to be 100% cleaned, they may be noisy actual.** If you intend to manually train models using this dataset, we recommend performing necessary preprocessing on the downloaded dataset to eliminate potential noisy samples (approximately 1% probability).
Here is the characters' preview:
| # | Images | Download | Preview 1 | Preview 2 | Preview 3 | Preview 4 | Preview 5 | Preview 6 | Preview 7 | Preview 8 |
|:------|---------:|:---------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|
| 0 | 499 | [Download](0/dataset.zip) |  |  |  |  |  |  |  |  |
| 1 | 18 | [Download](1/dataset.zip) |  |  |  |  |  |  |  |  |
| 2 | 18 | [Download](2/dataset.zip) |  |  |  |  |  |  |  |  |
| 3 | 58 | [Download](3/dataset.zip) |  |  |  |  |  |  |  |  |
| 4 | 229 | [Download](4/dataset.zip) |  |  |  |  |  |  |  |  |
| 5 | 22 | [Download](5/dataset.zip) |  |  |  |  |  |  |  |  |
| 6 | 49 | [Download](6/dataset.zip) |  |  |  |  |  |  |  |  |
| 7 | 33 | [Download](7/dataset.zip) |  |  |  |  |  |  |  |  |
| 8 | 19 | [Download](8/dataset.zip) |  |  |  |  |  |  |  |  |
| 9 | 88 | [Download](9/dataset.zip) |  |  |  |  |  |  |  |  |
| 10 | 276 | [Download](10/dataset.zip) |  |  |  |  |  |  |  |  |
| 11 | 26 | [Download](11/dataset.zip) |  |  |  |  |  |  |  |  |
| 12 | 74 | [Download](12/dataset.zip) |  |  |  |  |  |  |  |  |
| 13 | 37 | [Download](13/dataset.zip) |  |  |  |  |  |  |  |  |
| 14 | 76 | [Download](14/dataset.zip) |  |  |  |  |  |  |  |  |
| 15 | 40 | [Download](15/dataset.zip) |  |  |  |  |  |  |  |  |
| 16 | 151 | [Download](16/dataset.zip) |  |  |  |  |  |  |  |  |
| 17 | 9 | [Download](17/dataset.zip) |  |  |  |  |  |  |  |  |
| 18 | 24 | [Download](18/dataset.zip) |  |  |  |  |  |  |  |  |
| 19 | 14 | [Download](19/dataset.zip) |  |  |  |  |  |  |  |  |
| 20 | 9 | [Download](20/dataset.zip) |  |  |  |  |  |  |  |  |
| 21 | 14 | [Download](21/dataset.zip) |  |  |  |  |  |  |  |  |
| 22 | 41 | [Download](22/dataset.zip) |  |  |  |  |  |  |  |  |
| noise | 108 | [Download](-1/dataset.zip) |  |  |  |  |  |  |  |  |
| BangumiBase/angelbeats | [
"size_categories:1K<n<10K",
"license:mit",
"art",
"region:us"
] | 2023-11-30T10:11:35+00:00 | {"license": "mit", "size_categories": ["1K<n<10K"], "tags": ["art"]} | 2023-11-30T11:44:23+00:00 | [] | [] | TAGS
#size_categories-1K<n<10K #license-mit #art #region-us
| Bangumi Image Base of Angel Beats!
==================================
This is the image base of bangumi Angel Beats!, we detected 24 characters, 1932 images in total. The full dataset is here.
Please note that these image bases are not guaranteed to be 100% cleaned, they may be noisy actual. If you intend to manually train models using this dataset, we recommend performing necessary preprocessing on the downloaded dataset to eliminate potential noisy samples (approximately 1% probability).
Here is the characters' preview:
| [] | [
"TAGS\n#size_categories-1K<n<10K #license-mit #art #region-us \n"
] | [
25
] | [
"passage: TAGS\n#size_categories-1K<n<10K #license-mit #art #region-us \n"
] |
50c437558474206e773a185c4a0f900f76185e96 |
# Bangumi Image Base of Darker Than Black
This is the image base of bangumi Darker Than Black, we detected 74 characters, 4730 images in total. The full dataset is [here](all.zip).
**Please note that these image bases are not guaranteed to be 100% cleaned, they may be noisy actual.** If you intend to manually train models using this dataset, we recommend performing necessary preprocessing on the downloaded dataset to eliminate potential noisy samples (approximately 1% probability).
Here is the characters' preview:
| # | Images | Download | Preview 1 | Preview 2 | Preview 3 | Preview 4 | Preview 5 | Preview 6 | Preview 7 | Preview 8 |
|:------|---------:|:---------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|
| 0 | 82 | [Download](0/dataset.zip) |  |  |  |  |  |  |  |  |
| 1 | 583 | [Download](1/dataset.zip) |  |  |  |  |  |  |  |  |
| 2 | 38 | [Download](2/dataset.zip) |  |  |  |  |  |  |  |  |
| 3 | 57 | [Download](3/dataset.zip) |  |  |  |  |  |  |  |  |
| 4 | 71 | [Download](4/dataset.zip) |  |  |  |  |  |  |  |  |
| 5 | 149 | [Download](5/dataset.zip) |  |  |  |  |  |  |  |  |
| 6 | 28 | [Download](6/dataset.zip) |  |  |  |  |  |  |  |  |
| 7 | 33 | [Download](7/dataset.zip) |  |  |  |  |  |  |  |  |
| 8 | 50 | [Download](8/dataset.zip) |  |  |  |  |  |  |  |  |
| 9 | 35 | [Download](9/dataset.zip) |  |  |  |  |  |  |  |  |
| 10 | 82 | [Download](10/dataset.zip) |  |  |  |  |  |  |  |  |
| 11 | 112 | [Download](11/dataset.zip) |  |  |  |  |  |  |  |  |
| 12 | 29 | [Download](12/dataset.zip) |  |  |  |  |  |  |  |  |
| 13 | 29 | [Download](13/dataset.zip) |  |  |  |  |  |  |  |  |
| 14 | 18 | [Download](14/dataset.zip) |  |  |  |  |  |  |  |  |
| 15 | 99 | [Download](15/dataset.zip) |  |  |  |  |  |  |  |  |
| 16 | 45 | [Download](16/dataset.zip) |  |  |  |  |  |  |  |  |
| 17 | 14 | [Download](17/dataset.zip) |  |  |  |  |  |  |  |  |
| 18 | 74 | [Download](18/dataset.zip) |  |  |  |  |  |  |  |  |
| 19 | 37 | [Download](19/dataset.zip) |  |  |  |  |  |  |  |  |
| 20 | 817 | [Download](20/dataset.zip) |  |  |  |  |  |  |  |  |
| 21 | 17 | [Download](21/dataset.zip) |  |  |  |  |  |  |  |  |
| 22 | 22 | [Download](22/dataset.zip) |  |  |  |  |  |  |  |  |
| 23 | 7 | [Download](23/dataset.zip) |  |  |  |  |  |  |  | N/A |
| 24 | 12 | [Download](24/dataset.zip) |  |  |  |  |  |  |  |  |
| 25 | 25 | [Download](25/dataset.zip) |  |  |  |  |  |  |  |  |
| 26 | 431 | [Download](26/dataset.zip) |  |  |  |  |  |  |  |  |
| 27 | 48 | [Download](27/dataset.zip) |  |  |  |  |  |  |  |  |
| 28 | 27 | [Download](28/dataset.zip) |  |  |  |  |  |  |  |  |
| 29 | 10 | [Download](29/dataset.zip) |  |  |  |  |  |  |  |  |
| 30 | 36 | [Download](30/dataset.zip) |  |  |  |  |  |  |  |  |
| 31 | 25 | [Download](31/dataset.zip) |  |  |  |  |  |  |  |  |
| 32 | 23 | [Download](32/dataset.zip) |  |  |  |  |  |  |  |  |
| 33 | 16 | [Download](33/dataset.zip) |  |  |  |  |  |  |  |  |
| 34 | 48 | [Download](34/dataset.zip) |  |  |  |  |  |  |  |  |
| 35 | 20 | [Download](35/dataset.zip) |  |  |  |  |  |  |  |  |
| 36 | 41 | [Download](36/dataset.zip) |  |  |  |  |  |  |  |  |
| 37 | 364 | [Download](37/dataset.zip) |  |  |  |  |  |  |  |  |
| 38 | 19 | [Download](38/dataset.zip) |  |  |  |  |  |  |  |  |
| 39 | 15 | [Download](39/dataset.zip) |  |  |  |  |  |  |  |  |
| 40 | 9 | [Download](40/dataset.zip) |  |  |  |  |  |  |  |  |
| 41 | 66 | [Download](41/dataset.zip) |  |  |  |  |  |  |  |  |
| 42 | 44 | [Download](42/dataset.zip) |  |  |  |  |  |  |  |  |
| 43 | 30 | [Download](43/dataset.zip) |  |  |  |  |  |  |  |  |
| 44 | 50 | [Download](44/dataset.zip) |  |  |  |  |  |  |  |  |
| 45 | 19 | [Download](45/dataset.zip) |  |  |  |  |  |  |  |  |
| 46 | 11 | [Download](46/dataset.zip) |  |  |  |  |  |  |  |  |
| 47 | 19 | [Download](47/dataset.zip) |  |  |  |  |  |  |  |  |
| 48 | 44 | [Download](48/dataset.zip) |  |  |  |  |  |  |  |  |
| 49 | 13 | [Download](49/dataset.zip) |  |  |  |  |  |  |  |  |
| 50 | 35 | [Download](50/dataset.zip) |  |  |  |  |  |  |  |  |
| 51 | 22 | [Download](51/dataset.zip) |  |  |  |  |  |  |  |  |
| 52 | 14 | [Download](52/dataset.zip) |  |  |  |  |  |  |  |  |
| 53 | 18 | [Download](53/dataset.zip) |  |  |  |  |  |  |  |  |
| 54 | 45 | [Download](54/dataset.zip) |  |  |  |  |  |  |  |  |
| 55 | 20 | [Download](55/dataset.zip) |  |  |  |  |  |  |  |  |
| 56 | 10 | [Download](56/dataset.zip) |  |  |  |  |  |  |  |  |
| 57 | 16 | [Download](57/dataset.zip) |  |  |  |  |  |  |  |  |
| 58 | 13 | [Download](58/dataset.zip) |  |  |  |  |  |  |  |  |
| 59 | 10 | [Download](59/dataset.zip) |  |  |  |  |  |  |  |  |
| 60 | 7 | [Download](60/dataset.zip) |  |  |  |  |  |  |  | N/A |
| 61 | 135 | [Download](61/dataset.zip) |  |  |  |  |  |  |  |  |
| 62 | 20 | [Download](62/dataset.zip) |  |  |  |  |  |  |  |  |
| 63 | 13 | [Download](63/dataset.zip) |  |  |  |  |  |  |  |  |
| 64 | 30 | [Download](64/dataset.zip) |  |  |  |  |  |  |  |  |
| 65 | 19 | [Download](65/dataset.zip) |  |  |  |  |  |  |  |  |
| 66 | 16 | [Download](66/dataset.zip) |  |  |  |  |  |  |  |  |
| 67 | 7 | [Download](67/dataset.zip) |  |  |  |  |  |  |  | N/A |
| 68 | 9 | [Download](68/dataset.zip) |  |  |  |  |  |  |  |  |
| 69 | 8 | [Download](69/dataset.zip) |  |  |  |  |  |  |  |  |
| 70 | 12 | [Download](70/dataset.zip) |  |  |  |  |  |  |  |  |
| 71 | 22 | [Download](71/dataset.zip) |  |  |  |  |  |  |  |  |
| 72 | 74 | [Download](72/dataset.zip) |  |  |  |  |  |  |  |  |
| noise | 162 | [Download](-1/dataset.zip) |  |  |  |  |  |  |  |  |
| BangumiBase/darkerthanblack | [
"size_categories:1K<n<10K",
"license:mit",
"art",
"region:us"
] | 2023-11-30T10:12:06+00:00 | {"license": "mit", "size_categories": ["1K<n<10K"], "tags": ["art"]} | 2023-11-30T13:08:55+00:00 | [] | [] | TAGS
#size_categories-1K<n<10K #license-mit #art #region-us
| Bangumi Image Base of Darker Than Black
=======================================
This is the image base of bangumi Darker Than Black, we detected 74 characters, 4730 images in total. The full dataset is here.
Please note that these image bases are not guaranteed to be 100% cleaned, they may be noisy actual. If you intend to manually train models using this dataset, we recommend performing necessary preprocessing on the downloaded dataset to eliminate potential noisy samples (approximately 1% probability).
Here is the characters' preview:
| [] | [
"TAGS\n#size_categories-1K<n<10K #license-mit #art #region-us \n"
] | [
25
] | [
"passage: TAGS\n#size_categories-1K<n<10K #license-mit #art #region-us \n"
] |
251a5a754d10f096e025745fe234da3d02b1ed2b |
# Bangumi Image Base of Dorohedoro
This is the image base of bangumi Dorohedoro, we detected 23 characters, 1018 images in total. The full dataset is [here](all.zip).
**Please note that these image bases are not guaranteed to be 100% cleaned, they may be noisy actual.** If you intend to manually train models using this dataset, we recommend performing necessary preprocessing on the downloaded dataset to eliminate potential noisy samples (approximately 1% probability).
Here is the characters' preview:
| # | Images | Download | Preview 1 | Preview 2 | Preview 3 | Preview 4 | Preview 5 | Preview 6 | Preview 7 | Preview 8 |
|:------|---------:|:---------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|
| 0 | 140 | [Download](0/dataset.zip) |  |  |  |  |  |  |  |  |
| 1 | 49 | [Download](1/dataset.zip) |  |  |  |  |  |  |  |  |
| 2 | 35 | [Download](2/dataset.zip) |  |  |  |  |  |  |  |  |
| 3 | 19 | [Download](3/dataset.zip) |  |  |  |  |  |  |  |  |
| 4 | 107 | [Download](4/dataset.zip) |  |  |  |  |  |  |  |  |
| 5 | 114 | [Download](5/dataset.zip) |  |  |  |  |  |  |  |  |
| 6 | 43 | [Download](6/dataset.zip) |  |  |  |  |  |  |  |  |
| 7 | 23 | [Download](7/dataset.zip) |  |  |  |  |  |  |  |  |
| 8 | 77 | [Download](8/dataset.zip) |  |  |  |  |  |  |  |  |
| 9 | 52 | [Download](9/dataset.zip) |  |  |  |  |  |  |  |  |
| 10 | 45 | [Download](10/dataset.zip) |  |  |  |  |  |  |  |  |
| 11 | 29 | [Download](11/dataset.zip) |  |  |  |  |  |  |  |  |
| 12 | 18 | [Download](12/dataset.zip) |  |  |  |  |  |  |  |  |
| 13 | 22 | [Download](13/dataset.zip) |  |  |  |  |  |  |  |  |
| 14 | 57 | [Download](14/dataset.zip) |  |  |  |  |  |  |  |  |
| 15 | 16 | [Download](15/dataset.zip) |  |  |  |  |  |  |  |  |
| 16 | 23 | [Download](16/dataset.zip) |  |  |  |  |  |  |  |  |
| 17 | 37 | [Download](17/dataset.zip) |  |  |  |  |  |  |  |  |
| 18 | 8 | [Download](18/dataset.zip) |  |  |  |  |  |  |  |  |
| 19 | 19 | [Download](19/dataset.zip) |  |  |  |  |  |  |  |  |
| 20 | 12 | [Download](20/dataset.zip) |  |  |  |  |  |  |  |  |
| 21 | 10 | [Download](21/dataset.zip) |  |  |  |  |  |  |  |  |
| noise | 63 | [Download](-1/dataset.zip) |  |  |  |  |  |  |  |  |
| BangumiBase/dorohedoro | [
"size_categories:1K<n<10K",
"license:mit",
"art",
"region:us"
] | 2023-11-30T10:12:38+00:00 | {"license": "mit", "size_categories": ["1K<n<10K"], "tags": ["art"]} | 2023-11-30T11:20:07+00:00 | [] | [] | TAGS
#size_categories-1K<n<10K #license-mit #art #region-us
| Bangumi Image Base of Dorohedoro
================================
This is the image base of bangumi Dorohedoro, we detected 23 characters, 1018 images in total. The full dataset is here.
Please note that these image bases are not guaranteed to be 100% cleaned, they may be noisy actual. If you intend to manually train models using this dataset, we recommend performing necessary preprocessing on the downloaded dataset to eliminate potential noisy samples (approximately 1% probability).
Here is the characters' preview:
| [] | [
"TAGS\n#size_categories-1K<n<10K #license-mit #art #region-us \n"
] | [
25
] | [
"passage: TAGS\n#size_categories-1K<n<10K #license-mit #art #region-us \n"
] |
e60b21c62ce570ab87648ee942da62440427bfda |
# Carla-COCO-Object-Detection-Dataset-No-Images
**Hugging Face COCO-Style Labelled Dataset for Object Detection in Carla Simulator**
This dataset contains 1028 images, each 640x380 pixels, with corresponding publically accessible URLs.
The dataset is split into 249 test and 779 training examples.
The dataset was collected in Carla Simulator, driving around in autopilot mode in various environments (Town01, Town02, Town03, Town04, Town05) and saving every i-th frame.
The labels where then automatically generated using the semantic segmentation information.
**Available classes are:**
* Automobile (Car, Truck)
* Bike
* Motorbike
* Traffic light
* Traffic sign
**Example image:**
**Example annotated image:**
## Dataset Structure
### Data Instances
A data point comprises an image, its file name, its publically accessible URL, and its object annotations.
```json
{
"image_id": 14,
"width": 640,
"height": 380,
"file_name": "Town01_001860.png",
"url": "https: //github.com/yunusskeete/Carla-COCO-Object-Detection-Dataset/raw/master/images/train/Town01_001860.png",
"objects": {
"id": [1, 2],
"area": [41650, 150],
"bbox": [
[201, 205, 238, 175],
[363, 159, 6, 25]
],
"category": [1, 4]
}
}
```
### Data Fields
* **image_id**: the image id
* **width**: the image width
* **height**: the image height
* **objects**: a dictionary containing bounding box metadata for the objects present on the image
* **id**: the annotation id
* **area**: the area of the bounding box
* **bbox**: the object's bounding box (in the coco format)
* **category**: the object's category, with possible values including automobile (1), bike (2), motorbike (3), traffic_light (4) and traffic_sign (5)
## Contributions
This repo is a fork from [Carla-Object-Detection-Dataset](https://github.com/DanielHfnr/Carla-Object-Detection-Dataset).
Acknowledgements are made to [DanielHfnr](https://github.com/DanielHfnr) for the original data collection and dataset preparation. | yunusskeete/Carla-COCO-Object-Detection-Dataset | [
"task_categories:object-detection",
"size_categories:n<1K",
"license:mit",
"region:us"
] | 2023-11-30T10:41:12+00:00 | {"license": "mit", "size_categories": ["n<1K"], "task_categories": ["object-detection"]} | 2023-12-04T23:57:01+00:00 | [] | [] | TAGS
#task_categories-object-detection #size_categories-n<1K #license-mit #region-us
|
# Carla-COCO-Object-Detection-Dataset-No-Images
Hugging Face COCO-Style Labelled Dataset for Object Detection in Carla Simulator
This dataset contains 1028 images, each 640x380 pixels, with corresponding publically accessible URLs.
The dataset is split into 249 test and 779 training examples.
The dataset was collected in Carla Simulator, driving around in autopilot mode in various environments (Town01, Town02, Town03, Town04, Town05) and saving every i-th frame.
The labels where then automatically generated using the semantic segmentation information.
Available classes are:
* Automobile (Car, Truck)
* Bike
* Motorbike
* Traffic light
* Traffic sign
Example image:
!example image
Example annotated image:
!example image with annotations
## Dataset Structure
### Data Instances
A data point comprises an image, its file name, its publically accessible URL, and its object annotations.
### Data Fields
* image_id: the image id
* width: the image width
* height: the image height
* objects: a dictionary containing bounding box metadata for the objects present on the image
* id: the annotation id
* area: the area of the bounding box
* bbox: the object's bounding box (in the coco format)
* category: the object's category, with possible values including automobile (1), bike (2), motorbike (3), traffic_light (4) and traffic_sign (5)
## Contributions
This repo is a fork from Carla-Object-Detection-Dataset.
Acknowledgements are made to DanielHfnr for the original data collection and dataset preparation. | [
"# Carla-COCO-Object-Detection-Dataset-No-Images\n\nHugging Face COCO-Style Labelled Dataset for Object Detection in Carla Simulator\n\nThis dataset contains 1028 images, each 640x380 pixels, with corresponding publically accessible URLs.\nThe dataset is split into 249 test and 779 training examples.\nThe dataset was collected in Carla Simulator, driving around in autopilot mode in various environments (Town01, Town02, Town03, Town04, Town05) and saving every i-th frame.\nThe labels where then automatically generated using the semantic segmentation information.\n\nAvailable classes are:\n\n* Automobile (Car, Truck)\n* Bike\n* Motorbike\n* Traffic light\n* Traffic sign\n\nExample image:\n\n!example image\n\nExample annotated image:\n\n!example image with annotations",
"## Dataset Structure",
"### Data Instances\nA data point comprises an image, its file name, its publically accessible URL, and its object annotations.",
"### Data Fields\n* image_id: the image id\n* width: the image width\n* height: the image height\n* objects: a dictionary containing bounding box metadata for the objects present on the image\n* id: the annotation id\n* area: the area of the bounding box\n* bbox: the object's bounding box (in the coco format)\n* category: the object's category, with possible values including automobile (1), bike (2), motorbike (3), traffic_light (4) and traffic_sign (5)",
"## Contributions\nThis repo is a fork from Carla-Object-Detection-Dataset.\nAcknowledgements are made to DanielHfnr for the original data collection and dataset preparation."
] | [
"TAGS\n#task_categories-object-detection #size_categories-n<1K #license-mit #region-us \n",
"# Carla-COCO-Object-Detection-Dataset-No-Images\n\nHugging Face COCO-Style Labelled Dataset for Object Detection in Carla Simulator\n\nThis dataset contains 1028 images, each 640x380 pixels, with corresponding publically accessible URLs.\nThe dataset is split into 249 test and 779 training examples.\nThe dataset was collected in Carla Simulator, driving around in autopilot mode in various environments (Town01, Town02, Town03, Town04, Town05) and saving every i-th frame.\nThe labels where then automatically generated using the semantic segmentation information.\n\nAvailable classes are:\n\n* Automobile (Car, Truck)\n* Bike\n* Motorbike\n* Traffic light\n* Traffic sign\n\nExample image:\n\n!example image\n\nExample annotated image:\n\n!example image with annotations",
"## Dataset Structure",
"### Data Instances\nA data point comprises an image, its file name, its publically accessible URL, and its object annotations.",
"### Data Fields\n* image_id: the image id\n* width: the image width\n* height: the image height\n* objects: a dictionary containing bounding box metadata for the objects present on the image\n* id: the annotation id\n* area: the area of the bounding box\n* bbox: the object's bounding box (in the coco format)\n* category: the object's category, with possible values including automobile (1), bike (2), motorbike (3), traffic_light (4) and traffic_sign (5)",
"## Contributions\nThis repo is a fork from Carla-Object-Detection-Dataset.\nAcknowledgements are made to DanielHfnr for the original data collection and dataset preparation."
] | [
32,
191,
6,
31,
116,
44
] | [
"passage: TAGS\n#task_categories-object-detection #size_categories-n<1K #license-mit #region-us \n# Carla-COCO-Object-Detection-Dataset-No-Images\n\nHugging Face COCO-Style Labelled Dataset for Object Detection in Carla Simulator\n\nThis dataset contains 1028 images, each 640x380 pixels, with corresponding publically accessible URLs.\nThe dataset is split into 249 test and 779 training examples.\nThe dataset was collected in Carla Simulator, driving around in autopilot mode in various environments (Town01, Town02, Town03, Town04, Town05) and saving every i-th frame.\nThe labels where then automatically generated using the semantic segmentation information.\n\nAvailable classes are:\n\n* Automobile (Car, Truck)\n* Bike\n* Motorbike\n* Traffic light\n* Traffic sign\n\nExample image:\n\n!example image\n\nExample annotated image:\n\n!example image with annotations## Dataset Structure### Data Instances\nA data point comprises an image, its file name, its publically accessible URL, and its object annotations.### Data Fields\n* image_id: the image id\n* width: the image width\n* height: the image height\n* objects: a dictionary containing bounding box metadata for the objects present on the image\n* id: the annotation id\n* area: the area of the bounding box\n* bbox: the object's bounding box (in the coco format)\n* category: the object's category, with possible values including automobile (1), bike (2), motorbike (3), traffic_light (4) and traffic_sign (5)## Contributions\nThis repo is a fork from Carla-Object-Detection-Dataset.\nAcknowledgements are made to DanielHfnr for the original data collection and dataset preparation."
] |
e6d825cf027bf5fa5e88c60dd5669d8f9ce63b4f |
# AgroSegNet
This dataset comprises synthetic images captured from a top-down perspective, featuring two distinct annotations: one for direct sunlight and another for human and plant segmentation.
# Example loader
## Install Hugging Face datasets package
```sh
pip install datasets
```
## Download the dataset
```python
from datasets import load_dataset
dataset = load_dataset("Menchen/AgroSegNet","default") # Change "default" to "default-tiny" to preview and test
```
## Load the data
Images and masks are stored as PIL, for example:
```python
dataset["train"][1]["image"] # PIL image to rendered image
dataset["train"][1]["label"] # PIL image to mask
```
| Menchen/AgroSegNet | [
"task_categories:image-segmentation",
"size_categories:10K<n<100K",
"license:mit",
"doi:10.57967/hf/1652",
"region:us"
] | 2023-11-30T11:08:00+00:00 | {"license": "mit", "size_categories": ["10K<n<100K"], "task_categories": ["image-segmentation"], "dataset_info": [{"config_name": "default", "features": [{"name": "image", "dtype": "image"}, {"name": "label", "dtype": "image"}], "splits": [{"name": "train", "num_bytes": 20624104160.0, "num_examples": 40000}, {"name": "test", "num_bytes": 5112305610.0, "num_examples": 10000}], "download_size": 25802886510, "dataset_size": 25736409770.0}, {"config_name": "default-tiny", "features": [{"name": "image", "dtype": "image"}, {"name": "label", "dtype": "image"}], "splits": [{"name": "train", "num_bytes": 5141667600.0, "num_examples": 10000}, {"name": "test", "num_bytes": 1287848481.0, "num_examples": 2500}], "download_size": 6434219116, "dataset_size": 6429516081.0}, {"config_name": "human-plant", "features": [{"name": "image", "dtype": "image"}, {"name": "label", "dtype": "image"}], "splits": [{"name": "train", "num_bytes": 20529582920, "num_examples": 40000}, {"name": "test", "num_bytes": 5084631770, "num_examples": 10000}], "download_size": 25675082023, "dataset_size": 25614214690}, {"config_name": "human-plant-tiny", "features": [{"name": "image", "dtype": "image"}, {"name": "label", "dtype": "image"}], "splits": [{"name": "train", "num_bytes": 5117076360, "num_examples": 10000}, {"name": "test", "num_bytes": 1280707488.5, "num_examples": 2500}], "download_size": 6400701649, "dataset_size": 6397783848.5}], "configs": [{"config_name": "default", "data_files": [{"split": "train", "path": "data/train-*"}, {"split": "test", "path": "data/test-*"}]}, {"config_name": "default-tiny", "data_files": [{"split": "train", "path": "default-tiny/train-*"}, {"split": "test", "path": "default-tiny/test-*"}]}, {"config_name": "human-plant", "data_files": [{"split": "train", "path": "human-plant/train-*"}, {"split": "test", "path": "human-plant/test-*"}]}, {"config_name": "human-plant-tiny", "data_files": [{"split": "train", "path": "human-plant-tiny/train-*"}, {"split": "test", "path": "human-plant-tiny/test-*"}]}]} | 2024-01-17T14:40:25+00:00 | [] | [] | TAGS
#task_categories-image-segmentation #size_categories-10K<n<100K #license-mit #doi-10.57967/hf/1652 #region-us
|
# AgroSegNet
This dataset comprises synthetic images captured from a top-down perspective, featuring two distinct annotations: one for direct sunlight and another for human and plant segmentation.
# Example loader
## Install Hugging Face datasets package
## Download the dataset
## Load the data
Images and masks are stored as PIL, for example:
| [
"# AgroSegNet\n\nThis dataset comprises synthetic images captured from a top-down perspective, featuring two distinct annotations: one for direct sunlight and another for human and plant segmentation.",
"# Example loader",
"## Install Hugging Face datasets package",
"## Download the dataset",
"## Load the data\n\nImages and masks are stored as PIL, for example:"
] | [
"TAGS\n#task_categories-image-segmentation #size_categories-10K<n<100K #license-mit #doi-10.57967/hf/1652 #region-us \n",
"# AgroSegNet\n\nThis dataset comprises synthetic images captured from a top-down perspective, featuring two distinct annotations: one for direct sunlight and another for human and plant segmentation.",
"# Example loader",
"## Install Hugging Face datasets package",
"## Download the dataset",
"## Load the data\n\nImages and masks are stored as PIL, for example:"
] | [
47,
44,
5,
9,
5,
19
] | [
"passage: TAGS\n#task_categories-image-segmentation #size_categories-10K<n<100K #license-mit #doi-10.57967/hf/1652 #region-us \n# AgroSegNet\n\nThis dataset comprises synthetic images captured from a top-down perspective, featuring two distinct annotations: one for direct sunlight and another for human and plant segmentation.# Example loader## Install Hugging Face datasets package## Download the dataset## Load the data\n\nImages and masks are stored as PIL, for example:"
] |
abed741d19e058b5f64b4e3c8c906dfaf656162b |
# Dataset Card for Dataset Name
<!-- Provide a quick summary of the dataset. -->
This dataset card aims to be a base template for new datasets. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/datasetcard_template.md?plain=1).
## Dataset Details
### Dataset Description
<!-- Provide a longer summary of what this dataset is. -->
- **Curated by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
### Dataset Sources [optional]
<!-- Provide the basic links for the dataset. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the dataset is intended to be used. -->
### Direct Use
<!-- This section describes suitable use cases for the dataset. -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the dataset will not work well for. -->
[More Information Needed]
## Dataset Structure
<!-- This section provides a description of the dataset fields, and additional information about the dataset structure such as criteria used to create the splits, relationships between data points, etc. -->
[More Information Needed]
## Dataset Creation
### Curation Rationale
<!-- Motivation for the creation of this dataset. -->
[More Information Needed]
### Source Data
<!-- This section describes the source data (e.g. news text and headlines, social media posts, translated sentences, ...). -->
#### Data Collection and Processing
<!-- This section describes the data collection and processing process such as data selection criteria, filtering and normalization methods, tools and libraries used, etc. -->
[More Information Needed]
#### Who are the source data producers?
<!-- This section describes the people or systems who originally created the data. It should also include self-reported demographic or identity information for the source data creators if this information is available. -->
[More Information Needed]
### Annotations [optional]
<!-- If the dataset contains annotations which are not part of the initial data collection, use this section to describe them. -->
#### Annotation process
<!-- This section describes the annotation process such as annotation tools used in the process, the amount of data annotated, annotation guidelines provided to the annotators, interannotator statistics, annotation validation, etc. -->
[More Information Needed]
#### Who are the annotators?
<!-- This section describes the people or systems who created the annotations. -->
[More Information Needed]
#### Personal and Sensitive Information
<!-- State whether the dataset contains data that might be considered personal, sensitive, or private (e.g., data that reveals addresses, uniquely identifiable names or aliases, racial or ethnic origins, sexual orientations, religious beliefs, political opinions, financial or health data, etc.). If efforts were made to anonymize the data, describe the anonymization process. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users should be made aware of the risks, biases and limitations of the dataset. More information needed for further recommendations.
## Citation [optional]
<!-- If there is a paper or blog post introducing the dataset, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the dataset or dataset card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Dataset Card Authors [optional]
[More Information Needed]
## Dataset Card Contact
[More Information Needed] | OmkarVaidya1212/demo | [
"license:cc-by-4.0",
"region:us"
] | 2023-11-30T11:19:10+00:00 | {"license": "cc-by-4.0"} | 2023-11-30T11:28:16+00:00 | [] | [] | TAGS
#license-cc-by-4.0 #region-us
|
# Dataset Card for Dataset Name
This dataset card aims to be a base template for new datasets. It has been generated using this raw template.
## Dataset Details
### Dataset Description
- Curated by:
- Funded by [optional]:
- Shared by [optional]:
- Language(s) (NLP):
- License:
### Dataset Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Out-of-Scope Use
## Dataset Structure
## Dataset Creation
### Curation Rationale
### Source Data
#### Data Collection and Processing
#### Who are the source data producers?
### Annotations [optional]
#### Annotation process
#### Who are the annotators?
#### Personal and Sensitive Information
## Bias, Risks, and Limitations
### Recommendations
Users should be made aware of the risks, biases and limitations of the dataset. More information needed for further recommendations.
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Dataset Card Authors [optional]
## Dataset Card Contact
| [
"# Dataset Card for Dataset Name\n\n\n\nThis dataset card aims to be a base template for new datasets. It has been generated using this raw template.",
"## Dataset Details",
"### Dataset Description\n\n\n\n\n\n- Curated by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Language(s) (NLP): \n- License:",
"### Dataset Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Out-of-Scope Use",
"## Dataset Structure",
"## Dataset Creation",
"### Curation Rationale",
"### Source Data",
"#### Data Collection and Processing",
"#### Who are the source data producers?",
"### Annotations [optional]",
"#### Annotation process",
"#### Who are the annotators?",
"#### Personal and Sensitive Information",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers should be made aware of the risks, biases and limitations of the dataset. More information needed for further recommendations.\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Dataset Card Authors [optional]",
"## Dataset Card Contact"
] | [
"TAGS\n#license-cc-by-4.0 #region-us \n",
"# Dataset Card for Dataset Name\n\n\n\nThis dataset card aims to be a base template for new datasets. It has been generated using this raw template.",
"## Dataset Details",
"### Dataset Description\n\n\n\n\n\n- Curated by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Language(s) (NLP): \n- License:",
"### Dataset Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Out-of-Scope Use",
"## Dataset Structure",
"## Dataset Creation",
"### Curation Rationale",
"### Source Data",
"#### Data Collection and Processing",
"#### Who are the source data producers?",
"### Annotations [optional]",
"#### Annotation process",
"#### Who are the annotators?",
"#### Personal and Sensitive Information",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers should be made aware of the risks, biases and limitations of the dataset. More information needed for further recommendations.\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Dataset Card Authors [optional]",
"## Dataset Card Contact"
] | [
15,
34,
4,
40,
29,
3,
4,
9,
6,
5,
7,
4,
7,
10,
9,
5,
9,
8,
10,
46,
8,
7,
10,
5
] | [
"passage: TAGS\n#license-cc-by-4.0 #region-us \n# Dataset Card for Dataset Name\n\n\n\nThis dataset card aims to be a base template for new datasets. It has been generated using this raw template.## Dataset Details### Dataset Description\n\n\n\n\n\n- Curated by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Language(s) (NLP): \n- License:### Dataset Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:## Uses### Direct Use### Out-of-Scope Use## Dataset Structure## Dataset Creation### Curation Rationale### Source Data#### Data Collection and Processing#### Who are the source data producers?### Annotations [optional]#### Annotation process#### Who are the annotators?#### Personal and Sensitive Information## Bias, Risks, and Limitations### Recommendations\n\n\n\nUsers should be made aware of the risks, biases and limitations of the dataset. More information needed for further recommendations.\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:## Glossary [optional]## More Information [optional]## Dataset Card Authors [optional]## Dataset Card Contact"
] |
34fa236710010977e09934bbb9c38b2c0b0b01e6 |
The dataset published in the LREC 2022 paper "Large-Scale Hate Speech Detection with Cross-Domain Transfer".
# This is Dataset v1:
The original dataset that includes 100,000 tweets in English. The annotations with more than 60% agreement are included.
TweetID: Tweet ID from Twitter API
LangID: 1 (English)
TopicID: Domain of the topic 0-Religion, 1-Gender, 2-Race, 3-Politics, 4-Sports
HateLabel: Final hate label decision 0-Normal, 1-Offensive, 2-Hate
# GitHub Repo:
https://github.com/avaapm/hatespeech
# Citation:
Toraman, C., Şahinuç, F., & Yilmaz, E. (2022, June). Large-Scale Hate Speech Detection with Cross-Domain Transfer. In Proceedings of the Thirteenth Language Resources and Evaluation Conference (pp. 2215-2225). | ctoraman/large-scale-hate-speech-v1 | [
"task_categories:text-classification",
"language:en",
"license:cc-by-nc-sa-4.0",
"hate speech",
"hate speech detection",
"hate-speech",
"tweets",
"social media",
"topic",
"hate-speech-detection",
"region:us"
] | 2023-11-30T11:32:35+00:00 | {"language": ["en"], "license": "cc-by-nc-sa-4.0", "task_categories": ["text-classification"], "tags": ["hate speech", "hate speech detection", "hate-speech", "tweets", "social media", "topic", "hate-speech-detection"]} | 2023-11-30T11:41:18+00:00 | [] | [
"en"
] | TAGS
#task_categories-text-classification #language-English #license-cc-by-nc-sa-4.0 #hate speech #hate speech detection #hate-speech #tweets #social media #topic #hate-speech-detection #region-us
|
The dataset published in the LREC 2022 paper "Large-Scale Hate Speech Detection with Cross-Domain Transfer".
# This is Dataset v1:
The original dataset that includes 100,000 tweets in English. The annotations with more than 60% agreement are included.
TweetID: Tweet ID from Twitter API
LangID: 1 (English)
TopicID: Domain of the topic 0-Religion, 1-Gender, 2-Race, 3-Politics, 4-Sports
HateLabel: Final hate label decision 0-Normal, 1-Offensive, 2-Hate
# GitHub Repo:
URL
:
Toraman, C., Şahinuç, F., & Yilmaz, E. (2022, June). Large-Scale Hate Speech Detection with Cross-Domain Transfer. In Proceedings of the Thirteenth Language Resources and Evaluation Conference (pp. 2215-2225). | [
"# This is Dataset v1: \nThe original dataset that includes 100,000 tweets in English. The annotations with more than 60% agreement are included.\n\nTweetID: \tTweet ID from Twitter API\n\nLangID: \t1 (English)\n\nTopicID: \tDomain of the topic 0-Religion, 1-Gender, 2-Race, 3-Politics, 4-Sports\n\nHateLabel: \tFinal hate label decision 0-Normal, 1-Offensive, 2-Hate",
"# GitHub Repo: \nURL\n\n:\nToraman, C., Şahinuç, F., & Yilmaz, E. (2022, June). Large-Scale Hate Speech Detection with Cross-Domain Transfer. In Proceedings of the Thirteenth Language Resources and Evaluation Conference (pp. 2215-2225)."
] | [
"TAGS\n#task_categories-text-classification #language-English #license-cc-by-nc-sa-4.0 #hate speech #hate speech detection #hate-speech #tweets #social media #topic #hate-speech-detection #region-us \n",
"# This is Dataset v1: \nThe original dataset that includes 100,000 tweets in English. The annotations with more than 60% agreement are included.\n\nTweetID: \tTweet ID from Twitter API\n\nLangID: \t1 (English)\n\nTopicID: \tDomain of the topic 0-Religion, 1-Gender, 2-Race, 3-Politics, 4-Sports\n\nHateLabel: \tFinal hate label decision 0-Normal, 1-Offensive, 2-Hate",
"# GitHub Repo: \nURL\n\n:\nToraman, C., Şahinuç, F., & Yilmaz, E. (2022, June). Large-Scale Hate Speech Detection with Cross-Domain Transfer. In Proceedings of the Thirteenth Language Resources and Evaluation Conference (pp. 2215-2225)."
] | [
67,
98,
74
] | [
"passage: TAGS\n#task_categories-text-classification #language-English #license-cc-by-nc-sa-4.0 #hate speech #hate speech detection #hate-speech #tweets #social media #topic #hate-speech-detection #region-us \n# This is Dataset v1: \nThe original dataset that includes 100,000 tweets in English. The annotations with more than 60% agreement are included.\n\nTweetID: \tTweet ID from Twitter API\n\nLangID: \t1 (English)\n\nTopicID: \tDomain of the topic 0-Religion, 1-Gender, 2-Race, 3-Politics, 4-Sports\n\nHateLabel: \tFinal hate label decision 0-Normal, 1-Offensive, 2-Hate# GitHub Repo: \nURL\n\n:\nToraman, C., Şahinuç, F., & Yilmaz, E. (2022, June). Large-Scale Hate Speech Detection with Cross-Domain Transfer. In Proceedings of the Thirteenth Language Resources and Evaluation Conference (pp. 2215-2225)."
] |
b67887e255405b6d6dd5065cf2aa24254e05206a |
The dataset published in the LREC 2022 paper "Large-Scale Hate Speech Detection with Cross-Domain Transfer".
# This is Dataset v2:
The modified dataset that includes 68,597 tweets in English. The annotations with more than 80% agreement are included.
TweetID: Tweet ID from Twitter API
LangID: 1 (English)
TopicID: Domain of the topic 0-Religion, 1-Gender, 2-Race, 3-Politics, 4-Sports
HateLabel: Final hate label decision 0-Normal, 1-Offensive, 2-Hate
# GitHub Repo:
https://github.com/avaapm/hatespeech
# Citation:
Toraman, C., Şahinuç, F., & Yilmaz, E. (2022, June). Large-Scale Hate Speech Detection with Cross-Domain Transfer. In Proceedings of the Thirteenth Language Resources and Evaluation Conference (pp. 2215-2225). | ctoraman/large-scale-hate-speech-v2 | [
"task_categories:text-classification",
"language:en",
"license:cc-by-nc-sa-4.0",
"hate speech",
"hate speech detection",
"hate-speech",
"tweets",
"social media",
"topic",
"hate-speech-detection",
"region:us"
] | 2023-11-30T11:41:59+00:00 | {"language": ["en"], "license": "cc-by-nc-sa-4.0", "task_categories": ["text-classification"], "tags": ["hate speech", "hate speech detection", "hate-speech", "tweets", "social media", "topic", "hate-speech-detection"]} | 2023-11-30T11:50:49+00:00 | [] | [
"en"
] | TAGS
#task_categories-text-classification #language-English #license-cc-by-nc-sa-4.0 #hate speech #hate speech detection #hate-speech #tweets #social media #topic #hate-speech-detection #region-us
|
The dataset published in the LREC 2022 paper "Large-Scale Hate Speech Detection with Cross-Domain Transfer".
# This is Dataset v2:
The modified dataset that includes 68,597 tweets in English. The annotations with more than 80% agreement are included.
TweetID: Tweet ID from Twitter API
LangID: 1 (English)
TopicID: Domain of the topic 0-Religion, 1-Gender, 2-Race, 3-Politics, 4-Sports
HateLabel: Final hate label decision 0-Normal, 1-Offensive, 2-Hate
# GitHub Repo:
URL
:
Toraman, C., Şahinuç, F., & Yilmaz, E. (2022, June). Large-Scale Hate Speech Detection with Cross-Domain Transfer. In Proceedings of the Thirteenth Language Resources and Evaluation Conference (pp. 2215-2225). | [
"# This is Dataset v2: \nThe modified dataset that includes 68,597 tweets in English. The annotations with more than 80% agreement are included.\n\nTweetID: \tTweet ID from Twitter API\n\nLangID: \t1 (English)\n\nTopicID: \tDomain of the topic 0-Religion, 1-Gender, 2-Race, 3-Politics, 4-Sports\n\nHateLabel: \tFinal hate label decision 0-Normal, 1-Offensive, 2-Hate",
"# GitHub Repo: \nURL\n\n:\nToraman, C., Şahinuç, F., & Yilmaz, E. (2022, June). Large-Scale Hate Speech Detection with Cross-Domain Transfer. In Proceedings of the Thirteenth Language Resources and Evaluation Conference (pp. 2215-2225)."
] | [
"TAGS\n#task_categories-text-classification #language-English #license-cc-by-nc-sa-4.0 #hate speech #hate speech detection #hate-speech #tweets #social media #topic #hate-speech-detection #region-us \n",
"# This is Dataset v2: \nThe modified dataset that includes 68,597 tweets in English. The annotations with more than 80% agreement are included.\n\nTweetID: \tTweet ID from Twitter API\n\nLangID: \t1 (English)\n\nTopicID: \tDomain of the topic 0-Religion, 1-Gender, 2-Race, 3-Politics, 4-Sports\n\nHateLabel: \tFinal hate label decision 0-Normal, 1-Offensive, 2-Hate",
"# GitHub Repo: \nURL\n\n:\nToraman, C., Şahinuç, F., & Yilmaz, E. (2022, June). Large-Scale Hate Speech Detection with Cross-Domain Transfer. In Proceedings of the Thirteenth Language Resources and Evaluation Conference (pp. 2215-2225)."
] | [
67,
100,
74
] | [
"passage: TAGS\n#task_categories-text-classification #language-English #license-cc-by-nc-sa-4.0 #hate speech #hate speech detection #hate-speech #tweets #social media #topic #hate-speech-detection #region-us \n# This is Dataset v2: \nThe modified dataset that includes 68,597 tweets in English. The annotations with more than 80% agreement are included.\n\nTweetID: \tTweet ID from Twitter API\n\nLangID: \t1 (English)\n\nTopicID: \tDomain of the topic 0-Religion, 1-Gender, 2-Race, 3-Politics, 4-Sports\n\nHateLabel: \tFinal hate label decision 0-Normal, 1-Offensive, 2-Hate# GitHub Repo: \nURL\n\n:\nToraman, C., Şahinuç, F., & Yilmaz, E. (2022, June). Large-Scale Hate Speech Detection with Cross-Domain Transfer. In Proceedings of the Thirteenth Language Resources and Evaluation Conference (pp. 2215-2225)."
] |
11b41ab693820e363242388678dc6d6d23c9b0c3 |
The dataset published in the LREC 2022 paper "Large-Scale Hate Speech Detection with Cross-Domain Transfer".
# This is Dataset v1 (Turkish):
The original dataset that includes 100,000 tweets in Turkish. The annotations with more than 60% agreement are included.
TweetID: Tweet ID from Twitter API
LangID: 0 (Turkish)
TopicID: Domain of the topic 0-Religion, 1-Gender, 2-Race, 3-Politics, 4-Sports
HateLabel: Final hate label decision 0-Normal, 1-Offensive, 2-Hate
# GitHub Repo:
https://github.com/avaapm/hatespeech
# Citation:
Toraman, C., Şahinuç, F., & Yilmaz, E. (2022, June). Large-Scale Hate Speech Detection with Cross-Domain Transfer. In Proceedings of the Thirteenth Language Resources and Evaluation Conference (pp. 2215-2225). | ctoraman/large-scale-hate-speech-turkish-v1 | [
"task_categories:text-classification",
"language:tr",
"license:cc-by-nc-sa-4.0",
"hate speech",
"hate speech detection",
"hate-speech",
"tweets",
"social media",
"topic",
"hate-speech-detection",
"region:us"
] | 2023-11-30T11:44:00+00:00 | {"language": ["tr"], "license": "cc-by-nc-sa-4.0", "task_categories": ["text-classification"], "tags": ["hate speech", "hate speech detection", "hate-speech", "tweets", "social media", "topic", "hate-speech-detection"]} | 2023-11-30T11:46:33+00:00 | [] | [
"tr"
] | TAGS
#task_categories-text-classification #language-Turkish #license-cc-by-nc-sa-4.0 #hate speech #hate speech detection #hate-speech #tweets #social media #topic #hate-speech-detection #region-us
|
The dataset published in the LREC 2022 paper "Large-Scale Hate Speech Detection with Cross-Domain Transfer".
# This is Dataset v1 (Turkish):
The original dataset that includes 100,000 tweets in Turkish. The annotations with more than 60% agreement are included.
TweetID: Tweet ID from Twitter API
LangID: 0 (Turkish)
TopicID: Domain of the topic 0-Religion, 1-Gender, 2-Race, 3-Politics, 4-Sports
HateLabel: Final hate label decision 0-Normal, 1-Offensive, 2-Hate
# GitHub Repo:
URL
:
Toraman, C., Şahinuç, F., & Yilmaz, E. (2022, June). Large-Scale Hate Speech Detection with Cross-Domain Transfer. In Proceedings of the Thirteenth Language Resources and Evaluation Conference (pp. 2215-2225). | [
"# This is Dataset v1 (Turkish): \nThe original dataset that includes 100,000 tweets in Turkish. The annotations with more than 60% agreement are included.\n\nTweetID: \tTweet ID from Twitter API\n\nLangID: \t0 (Turkish)\n\nTopicID: \tDomain of the topic 0-Religion, 1-Gender, 2-Race, 3-Politics, 4-Sports\n\nHateLabel: \tFinal hate label decision 0-Normal, 1-Offensive, 2-Hate",
"# GitHub Repo: \nURL\n\n:\nToraman, C., Şahinuç, F., & Yilmaz, E. (2022, June). Large-Scale Hate Speech Detection with Cross-Domain Transfer. In Proceedings of the Thirteenth Language Resources and Evaluation Conference (pp. 2215-2225)."
] | [
"TAGS\n#task_categories-text-classification #language-Turkish #license-cc-by-nc-sa-4.0 #hate speech #hate speech detection #hate-speech #tweets #social media #topic #hate-speech-detection #region-us \n",
"# This is Dataset v1 (Turkish): \nThe original dataset that includes 100,000 tweets in Turkish. The annotations with more than 60% agreement are included.\n\nTweetID: \tTweet ID from Twitter API\n\nLangID: \t0 (Turkish)\n\nTopicID: \tDomain of the topic 0-Religion, 1-Gender, 2-Race, 3-Politics, 4-Sports\n\nHateLabel: \tFinal hate label decision 0-Normal, 1-Offensive, 2-Hate",
"# GitHub Repo: \nURL\n\n:\nToraman, C., Şahinuç, F., & Yilmaz, E. (2022, June). Large-Scale Hate Speech Detection with Cross-Domain Transfer. In Proceedings of the Thirteenth Language Resources and Evaluation Conference (pp. 2215-2225)."
] | [
69,
106,
74
] | [
"passage: TAGS\n#task_categories-text-classification #language-Turkish #license-cc-by-nc-sa-4.0 #hate speech #hate speech detection #hate-speech #tweets #social media #topic #hate-speech-detection #region-us \n# This is Dataset v1 (Turkish): \nThe original dataset that includes 100,000 tweets in Turkish. The annotations with more than 60% agreement are included.\n\nTweetID: \tTweet ID from Twitter API\n\nLangID: \t0 (Turkish)\n\nTopicID: \tDomain of the topic 0-Religion, 1-Gender, 2-Race, 3-Politics, 4-Sports\n\nHateLabel: \tFinal hate label decision 0-Normal, 1-Offensive, 2-Hate# GitHub Repo: \nURL\n\n:\nToraman, C., Şahinuç, F., & Yilmaz, E. (2022, June). Large-Scale Hate Speech Detection with Cross-Domain Transfer. In Proceedings of the Thirteenth Language Resources and Evaluation Conference (pp. 2215-2225)."
] |
83d11475f1335eacc949e737b9af49852b96eae1 |
The dataset published in the LREC 2022 paper "Large-Scale Hate Speech Detection with Cross-Domain Transfer".
# This is Dataset v2 (Turkish):
The modified dataset that includes 60,310 tweets in Turkish. The annotations with more than 80% agreement are included.
TweetID: Tweet ID from Twitter API
LangID: 0 (Turkish)
TopicID: Domain of the topic 0-Religion, 1-Gender, 2-Race, 3-Politics, 4-Sports
HateLabel: Final hate label decision 0-Normal, 1-Offensive, 2-Hate
# GitHub Repo:
https://github.com/avaapm/hatespeech
# Citation:
Toraman, C., Şahinuç, F., & Yilmaz, E. (2022, June). Large-Scale Hate Speech Detection with Cross-Domain Transfer. In Proceedings of the Thirteenth Language Resources and Evaluation Conference (pp. 2215-2225). | ctoraman/large-scale-hate-speech-turkish-v2 | [
"task_categories:text-classification",
"language:tr",
"license:cc-by-nc-sa-4.0",
"hate speech",
"hate speech detection",
"hate-speech",
"tweets",
"social media",
"topic",
"hate-speech-detection",
"region:us"
] | 2023-11-30T11:47:37+00:00 | {"language": ["tr"], "license": "cc-by-nc-sa-4.0", "task_categories": ["text-classification"], "tags": ["hate speech", "hate speech detection", "hate-speech", "tweets", "social media", "topic", "hate-speech-detection"]} | 2023-11-30T11:49:38+00:00 | [] | [
"tr"
] | TAGS
#task_categories-text-classification #language-Turkish #license-cc-by-nc-sa-4.0 #hate speech #hate speech detection #hate-speech #tweets #social media #topic #hate-speech-detection #region-us
|
The dataset published in the LREC 2022 paper "Large-Scale Hate Speech Detection with Cross-Domain Transfer".
# This is Dataset v2 (Turkish):
The modified dataset that includes 60,310 tweets in Turkish. The annotations with more than 80% agreement are included.
TweetID: Tweet ID from Twitter API
LangID: 0 (Turkish)
TopicID: Domain of the topic 0-Religion, 1-Gender, 2-Race, 3-Politics, 4-Sports
HateLabel: Final hate label decision 0-Normal, 1-Offensive, 2-Hate
# GitHub Repo:
URL
:
Toraman, C., Şahinuç, F., & Yilmaz, E. (2022, June). Large-Scale Hate Speech Detection with Cross-Domain Transfer. In Proceedings of the Thirteenth Language Resources and Evaluation Conference (pp. 2215-2225). | [
"# This is Dataset v2 (Turkish): \nThe modified dataset that includes 60,310 tweets in Turkish. The annotations with more than 80% agreement are included.\n\nTweetID: \tTweet ID from Twitter API\n\nLangID: \t0 (Turkish)\n\nTopicID: \tDomain of the topic 0-Religion, 1-Gender, 2-Race, 3-Politics, 4-Sports\n\nHateLabel: \tFinal hate label decision 0-Normal, 1-Offensive, 2-Hate",
"# GitHub Repo: \nURL\n\n:\nToraman, C., Şahinuç, F., & Yilmaz, E. (2022, June). Large-Scale Hate Speech Detection with Cross-Domain Transfer. In Proceedings of the Thirteenth Language Resources and Evaluation Conference (pp. 2215-2225)."
] | [
"TAGS\n#task_categories-text-classification #language-Turkish #license-cc-by-nc-sa-4.0 #hate speech #hate speech detection #hate-speech #tweets #social media #topic #hate-speech-detection #region-us \n",
"# This is Dataset v2 (Turkish): \nThe modified dataset that includes 60,310 tweets in Turkish. The annotations with more than 80% agreement are included.\n\nTweetID: \tTweet ID from Twitter API\n\nLangID: \t0 (Turkish)\n\nTopicID: \tDomain of the topic 0-Religion, 1-Gender, 2-Race, 3-Politics, 4-Sports\n\nHateLabel: \tFinal hate label decision 0-Normal, 1-Offensive, 2-Hate",
"# GitHub Repo: \nURL\n\n:\nToraman, C., Şahinuç, F., & Yilmaz, E. (2022, June). Large-Scale Hate Speech Detection with Cross-Domain Transfer. In Proceedings of the Thirteenth Language Resources and Evaluation Conference (pp. 2215-2225)."
] | [
69,
107,
74
] | [
"passage: TAGS\n#task_categories-text-classification #language-Turkish #license-cc-by-nc-sa-4.0 #hate speech #hate speech detection #hate-speech #tweets #social media #topic #hate-speech-detection #region-us \n# This is Dataset v2 (Turkish): \nThe modified dataset that includes 60,310 tweets in Turkish. The annotations with more than 80% agreement are included.\n\nTweetID: \tTweet ID from Twitter API\n\nLangID: \t0 (Turkish)\n\nTopicID: \tDomain of the topic 0-Religion, 1-Gender, 2-Race, 3-Politics, 4-Sports\n\nHateLabel: \tFinal hate label decision 0-Normal, 1-Offensive, 2-Hate# GitHub Repo: \nURL\n\n:\nToraman, C., Şahinuç, F., & Yilmaz, E. (2022, June). Large-Scale Hate Speech Detection with Cross-Domain Transfer. In Proceedings of the Thirteenth Language Resources and Evaluation Conference (pp. 2215-2225)."
] |
6a4667816c7280181febd7d5cb675a023a96ba60 | # MultiFactor-HotpotQA-SuppFacts
<!-- Provide a quick summary of the dataset. -->
The MultiFactor datasets -- SQuAD1.1-Zhou Split [1] in EMNLP 2023 Findings: [*Improving Question Generation with Multi-level Content Planning*](https://arxiv.org/abs/2310.13512).
## 1. Dataset Details
### 1.1 Dataset Description
SQuAD1.1-Zhou Split [1, 2] in EMNLP 2023 Findings: [*Improving Question Generation with Multi-level Content Planning*](https://arxiv.org/abs/2310.13512).
Based on the dataset in [2], we add the `p_hrase`, `n_phrase` and `full answer` attributes for every dataset instance.
The full answer is reconstructed with [QA2D](https://github.com/kelvinguu/qanli) [3]. More details are in paper github: https://github.com/zeaver/MultiFactor.
### 1.2 Dataset Sources
<!-- Provide the basic links for the dataset. -->
- **Repository:** https://github.com/zeaver/MultiFactor
- **Paper:** [*Improving Question Generation with Multi-level Content Planning*](https://arxiv.org/abs/2310.13512). EMNLP Findings, 2023.
## 2. Dataset Structure
```tex
.
├── dev.json
├── test.json
├── train.json
├── fa_model_inference
├── dev.json
├── test.json
└── train.json
```
Each split is a json file, not jsonl. Please load it with `json.load(f)` directly. And the dataset schema is:
```json
{
"context": "the given input context",
"answer": "the given answer",
"question": "the corresponding question",
"p_phrase": "the postive phrases in the given context",
"n_phrase": "the negative phrases",
"full answer": "pseudo-gold full answer (q + a -> a declarative sentence)",
}
```
We also provide the *FA_Model*'s inference results in `fa_model_inference/{split}.json`.
## 3. Dataset Card Contact
If you have any question, feel free to contact with me: [email protected]
## Reference
[1] Rajpurkar, Pranav, et al. [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://aclanthology.org/D16-1264/). EMNLP, 2016.
[2] Zhou, Qingyu, et al. [Neural Question Generation from Text: A Preliminary Study](https://arxiv.org/abs/1704.01792). EMNLP, 2017.
[3] Demszky, Dorottya, et al. [Transforming Question Answering Datasets Into Natural Language Inference Datasets](https://arxiv.org/abs/1809.02922). Stanford University. arXiv, 2018. | zeaver/multifactor_squad1.1_zhou | [
"task_categories:text-generation",
"task_categories:question-answering",
"size_categories:10K<n<100K",
"language:en",
"license:mit",
"question-generation",
"HotpotQA",
"arxiv:2310.13512",
"arxiv:1704.01792",
"arxiv:1809.02922",
"region:us"
] | 2023-11-30T12:02:02+00:00 | {"language": ["en"], "license": "mit", "size_categories": ["10K<n<100K"], "task_categories": ["text-generation", "question-answering"], "tags": ["question-generation", "HotpotQA"]} | 2023-11-30T12:26:36+00:00 | [
"2310.13512",
"1704.01792",
"1809.02922"
] | [
"en"
] | TAGS
#task_categories-text-generation #task_categories-question-answering #size_categories-10K<n<100K #language-English #license-mit #question-generation #HotpotQA #arxiv-2310.13512 #arxiv-1704.01792 #arxiv-1809.02922 #region-us
| # MultiFactor-HotpotQA-SuppFacts
The MultiFactor datasets -- SQuAD1.1-Zhou Split [1] in EMNLP 2023 Findings: *Improving Question Generation with Multi-level Content Planning*.
## 1. Dataset Details
### 1.1 Dataset Description
SQuAD1.1-Zhou Split [1, 2] in EMNLP 2023 Findings: *Improving Question Generation with Multi-level Content Planning*.
Based on the dataset in [2], we add the 'p_hrase', 'n_phrase' and 'full answer' attributes for every dataset instance.
The full answer is reconstructed with QA2D [3]. More details are in paper github: URL
### 1.2 Dataset Sources
- Repository: URL
- Paper: *Improving Question Generation with Multi-level Content Planning*. EMNLP Findings, 2023.
## 2. Dataset Structure
Each split is a json file, not jsonl. Please load it with 'URL(f)' directly. And the dataset schema is:
We also provide the *FA_Model*'s inference results in 'fa_model_inference/{split}.json'.
## 3. Dataset Card Contact
If you have any question, feel free to contact with me: zehua.xia1999@URL
## Reference
[1] Rajpurkar, Pranav, et al. SQuAD: 100,000+ Questions for Machine Comprehension of Text. EMNLP, 2016.
[2] Zhou, Qingyu, et al. Neural Question Generation from Text: A Preliminary Study. EMNLP, 2017.
[3] Demszky, Dorottya, et al. Transforming Question Answering Datasets Into Natural Language Inference Datasets. Stanford University. arXiv, 2018. | [
"# MultiFactor-HotpotQA-SuppFacts\n\n\n\nThe MultiFactor datasets -- SQuAD1.1-Zhou Split [1] in EMNLP 2023 Findings: *Improving Question Generation with Multi-level Content Planning*.",
"## 1. Dataset Details",
"### 1.1 Dataset Description\n\nSQuAD1.1-Zhou Split [1, 2] in EMNLP 2023 Findings: *Improving Question Generation with Multi-level Content Planning*. \n\nBased on the dataset in [2], we add the 'p_hrase', 'n_phrase' and 'full answer' attributes for every dataset instance. \nThe full answer is reconstructed with QA2D [3]. More details are in paper github: URL",
"### 1.2 Dataset Sources\n\n\n\n- Repository: URL\n- Paper: *Improving Question Generation with Multi-level Content Planning*. EMNLP Findings, 2023.",
"## 2. Dataset Structure\n\n\nEach split is a json file, not jsonl. Please load it with 'URL(f)' directly. And the dataset schema is:\n\n\n\nWe also provide the *FA_Model*'s inference results in 'fa_model_inference/{split}.json'.",
"## 3. Dataset Card Contact\n\nIf you have any question, feel free to contact with me: zehua.xia1999@URL",
"## Reference\n[1] Rajpurkar, Pranav, et al. SQuAD: 100,000+ Questions for Machine Comprehension of Text. EMNLP, 2016.\n\n[2] Zhou, Qingyu, et al. Neural Question Generation from Text: A Preliminary Study. EMNLP, 2017.\n\n[3] Demszky, Dorottya, et al. Transforming Question Answering Datasets Into Natural Language Inference Datasets. Stanford University. arXiv, 2018."
] | [
"TAGS\n#task_categories-text-generation #task_categories-question-answering #size_categories-10K<n<100K #language-English #license-mit #question-generation #HotpotQA #arxiv-2310.13512 #arxiv-1704.01792 #arxiv-1809.02922 #region-us \n",
"# MultiFactor-HotpotQA-SuppFacts\n\n\n\nThe MultiFactor datasets -- SQuAD1.1-Zhou Split [1] in EMNLP 2023 Findings: *Improving Question Generation with Multi-level Content Planning*.",
"## 1. Dataset Details",
"### 1.1 Dataset Description\n\nSQuAD1.1-Zhou Split [1, 2] in EMNLP 2023 Findings: *Improving Question Generation with Multi-level Content Planning*. \n\nBased on the dataset in [2], we add the 'p_hrase', 'n_phrase' and 'full answer' attributes for every dataset instance. \nThe full answer is reconstructed with QA2D [3]. More details are in paper github: URL",
"### 1.2 Dataset Sources\n\n\n\n- Repository: URL\n- Paper: *Improving Question Generation with Multi-level Content Planning*. EMNLP Findings, 2023.",
"## 2. Dataset Structure\n\n\nEach split is a json file, not jsonl. Please load it with 'URL(f)' directly. And the dataset schema is:\n\n\n\nWe also provide the *FA_Model*'s inference results in 'fa_model_inference/{split}.json'.",
"## 3. Dataset Card Contact\n\nIf you have any question, feel free to contact with me: zehua.xia1999@URL",
"## Reference\n[1] Rajpurkar, Pranav, et al. SQuAD: 100,000+ Questions for Machine Comprehension of Text. EMNLP, 2016.\n\n[2] Zhou, Qingyu, et al. Neural Question Generation from Text: A Preliminary Study. EMNLP, 2017.\n\n[3] Demszky, Dorottya, et al. Transforming Question Answering Datasets Into Natural Language Inference Datasets. Stanford University. arXiv, 2018."
] | [
87,
54,
5,
101,
39,
72,
26,
105
] | [
"passage: TAGS\n#task_categories-text-generation #task_categories-question-answering #size_categories-10K<n<100K #language-English #license-mit #question-generation #HotpotQA #arxiv-2310.13512 #arxiv-1704.01792 #arxiv-1809.02922 #region-us \n# MultiFactor-HotpotQA-SuppFacts\n\n\n\nThe MultiFactor datasets -- SQuAD1.1-Zhou Split [1] in EMNLP 2023 Findings: *Improving Question Generation with Multi-level Content Planning*.## 1. Dataset Details### 1.1 Dataset Description\n\nSQuAD1.1-Zhou Split [1, 2] in EMNLP 2023 Findings: *Improving Question Generation with Multi-level Content Planning*. \n\nBased on the dataset in [2], we add the 'p_hrase', 'n_phrase' and 'full answer' attributes for every dataset instance. \nThe full answer is reconstructed with QA2D [3]. More details are in paper github: URL### 1.2 Dataset Sources\n\n\n\n- Repository: URL\n- Paper: *Improving Question Generation with Multi-level Content Planning*. EMNLP Findings, 2023.## 2. Dataset Structure\n\n\nEach split is a json file, not jsonl. Please load it with 'URL(f)' directly. And the dataset schema is:\n\n\n\nWe also provide the *FA_Model*'s inference results in 'fa_model_inference/{split}.json'.## 3. Dataset Card Contact\n\nIf you have any question, feel free to contact with me: zehua.xia1999@URL## Reference\n[1] Rajpurkar, Pranav, et al. SQuAD: 100,000+ Questions for Machine Comprehension of Text. EMNLP, 2016.\n\n[2] Zhou, Qingyu, et al. Neural Question Generation from Text: A Preliminary Study. EMNLP, 2017.\n\n[3] Demszky, Dorottya, et al. Transforming Question Answering Datasets Into Natural Language Inference Datasets. Stanford University. arXiv, 2018."
] |
b303b267a00afc65ed5e364acabb35a3d9df5f5b | # mtkinit/ar_test
Created from AIOD platform | mtkinit/ar_test | [
"region:us"
] | 2023-11-30T12:03:23+00:00 | {"pretty_name": "mtkinit/ar_test"} | 2023-11-30T12:37:11+00:00 | [] | [] | TAGS
#region-us
| # mtkinit/ar_test
Created from AIOD platform | [
"# mtkinit/ar_test\nCreated from AIOD platform"
] | [
"TAGS\n#region-us \n",
"# mtkinit/ar_test\nCreated from AIOD platform"
] | [
6,
14
] | [
"passage: TAGS\n#region-us \n# mtkinit/ar_test\nCreated from AIOD platform"
] |
3c968fc6a34cb204f827a86504337b95a7a99e15 | # Dataset Card for "simple_pair"
```
@inproceedings{luo-etal-2022-simple-challenging,
title = "Simple but Challenging: Natural Language Inference Models Fail on Simple Sentences",
author = "Luo, Cheng and
Liu, Wei and
Lin, Jieyu and
Zou, Jiajie and
Xiang, Ming and
Ding, Nai",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2022",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-emnlp.252",
doi = "10.18653/v1/2022.findings-emnlp.252",
pages = "3449--3462",
}
``` | tasksource/simple_pair | [
"region:us"
] | 2023-11-30T12:09:55+00:00 | {"configs": [{"config_name": "default", "data_files": [{"split": "train", "path": "data/train-*"}, {"split": "test", "path": "data/test-*"}]}], "dataset_info": {"features": [{"name": "premise", "dtype": "string"}, {"name": "hypothesis", "dtype": "string"}, {"name": "label", "dtype": "string"}, {"name": "config", "dtype": "string"}], "splits": [{"name": "train", "num_bytes": 667441, "num_examples": 6000}, {"name": "test", "num_bytes": 24937007, "num_examples": 224000}], "download_size": 4749047, "dataset_size": 25604448}} | 2023-11-30T12:12:10+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "simple_pair"
| [
"# Dataset Card for \"simple_pair\""
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"simple_pair\""
] | [
6,
10
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"simple_pair\""
] |
90cd5e6b942d2e4ec4f2bf3b3f2f7c141d512475 | # Dataset Card for Dataset Name
<!-- Provide a quick summary of the dataset. -->
This dataset card aims to be a base template for new datasets. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/datasetcard_template.md?plain=1).
## Dataset Details
### Dataset Description
<!-- Provide a longer summary of what this dataset is. -->
- **Curated by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
### Dataset Sources [optional]
<!-- Provide the basic links for the dataset. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the dataset is intended to be used. -->
### Direct Use
<!-- This section describes suitable use cases for the dataset. -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the dataset will not work well for. -->
[More Information Needed]
## Dataset Structure
<!-- This section provides a description of the dataset fields, and additional information about the dataset structure such as criteria used to create the splits, relationships between data points, etc. -->
[More Information Needed]
## Dataset Creation
### Curation Rationale
<!-- Motivation for the creation of this dataset. -->
[More Information Needed]
### Source Data
<!-- This section describes the source data (e.g. news text and headlines, social media posts, translated sentences, ...). -->
#### Data Collection and Processing
<!-- This section describes the data collection and processing process such as data selection criteria, filtering and normalization methods, tools and libraries used, etc. -->
[More Information Needed]
#### Who are the source data producers?
<!-- This section describes the people or systems who originally created the data. It should also include self-reported demographic or identity information for the source data creators if this information is available. -->
[More Information Needed]
### Annotations [optional]
<!-- If the dataset contains annotations which are not part of the initial data collection, use this section to describe them. -->
#### Annotation process
<!-- This section describes the annotation process such as annotation tools used in the process, the amount of data annotated, annotation guidelines provided to the annotators, interannotator statistics, annotation validation, etc. -->
[More Information Needed]
#### Who are the annotators?
<!-- This section describes the people or systems who created the annotations. -->
[More Information Needed]
#### Personal and Sensitive Information
<!-- State whether the dataset contains data that might be considered personal, sensitive, or private (e.g., data that reveals addresses, uniquely identifiable names or aliases, racial or ethnic origins, sexual orientations, religious beliefs, political opinions, financial or health data, etc.). If efforts were made to anonymize the data, describe the anonymization process. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users should be made aware of the risks, biases and limitations of the dataset. More information needed for further recommendations.
## Citation [optional]
<!-- If there is a paper or blog post introducing the dataset, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the dataset or dataset card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Dataset Card Authors [optional]
[More Information Needed]
## Dataset Card Contact
[More Information Needed] | ducklovecode/candyImage2Image | [
"task_categories:text-generation",
"license:apache-2.0",
"region:us"
] | 2023-11-30T12:19:16+00:00 | {"license": "apache-2.0", "task_categories": ["text-generation"]} | 2023-12-02T03:15:43+00:00 | [] | [] | TAGS
#task_categories-text-generation #license-apache-2.0 #region-us
| # Dataset Card for Dataset Name
This dataset card aims to be a base template for new datasets. It has been generated using this raw template.
## Dataset Details
### Dataset Description
- Curated by:
- Funded by [optional]:
- Shared by [optional]:
- Language(s) (NLP):
- License:
### Dataset Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Out-of-Scope Use
## Dataset Structure
## Dataset Creation
### Curation Rationale
### Source Data
#### Data Collection and Processing
#### Who are the source data producers?
### Annotations [optional]
#### Annotation process
#### Who are the annotators?
#### Personal and Sensitive Information
## Bias, Risks, and Limitations
### Recommendations
Users should be made aware of the risks, biases and limitations of the dataset. More information needed for further recommendations.
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Dataset Card Authors [optional]
## Dataset Card Contact
| [
"# Dataset Card for Dataset Name\n\n\n\nThis dataset card aims to be a base template for new datasets. It has been generated using this raw template.",
"## Dataset Details",
"### Dataset Description\n\n\n\n\n\n- Curated by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Language(s) (NLP): \n- License:",
"### Dataset Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Out-of-Scope Use",
"## Dataset Structure",
"## Dataset Creation",
"### Curation Rationale",
"### Source Data",
"#### Data Collection and Processing",
"#### Who are the source data producers?",
"### Annotations [optional]",
"#### Annotation process",
"#### Who are the annotators?",
"#### Personal and Sensitive Information",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers should be made aware of the risks, biases and limitations of the dataset. More information needed for further recommendations.\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Dataset Card Authors [optional]",
"## Dataset Card Contact"
] | [
"TAGS\n#task_categories-text-generation #license-apache-2.0 #region-us \n",
"# Dataset Card for Dataset Name\n\n\n\nThis dataset card aims to be a base template for new datasets. It has been generated using this raw template.",
"## Dataset Details",
"### Dataset Description\n\n\n\n\n\n- Curated by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Language(s) (NLP): \n- License:",
"### Dataset Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Out-of-Scope Use",
"## Dataset Structure",
"## Dataset Creation",
"### Curation Rationale",
"### Source Data",
"#### Data Collection and Processing",
"#### Who are the source data producers?",
"### Annotations [optional]",
"#### Annotation process",
"#### Who are the annotators?",
"#### Personal and Sensitive Information",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers should be made aware of the risks, biases and limitations of the dataset. More information needed for further recommendations.\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Dataset Card Authors [optional]",
"## Dataset Card Contact"
] | [
25,
34,
4,
40,
29,
3,
4,
9,
6,
5,
7,
4,
7,
10,
9,
5,
9,
8,
10,
46,
8,
7,
10,
5
] | [
"passage: TAGS\n#task_categories-text-generation #license-apache-2.0 #region-us \n# Dataset Card for Dataset Name\n\n\n\nThis dataset card aims to be a base template for new datasets. It has been generated using this raw template.## Dataset Details### Dataset Description\n\n\n\n\n\n- Curated by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Language(s) (NLP): \n- License:### Dataset Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:## Uses### Direct Use### Out-of-Scope Use## Dataset Structure## Dataset Creation### Curation Rationale### Source Data#### Data Collection and Processing#### Who are the source data producers?### Annotations [optional]#### Annotation process#### Who are the annotators?#### Personal and Sensitive Information## Bias, Risks, and Limitations### Recommendations\n\n\n\nUsers should be made aware of the risks, biases and limitations of the dataset. More information needed for further recommendations.\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:## Glossary [optional]## More Information [optional]## Dataset Card Authors [optional]## Dataset Card Contact"
] |
45adef0a23d0800e64ccb485311137bfa1affe20 | # Dataset Card for "additional_charges_roles_v1"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | paul-w-qs/additional_charges_roles_v1 | [
"region:us"
] | 2023-11-30T12:27:42+00:00 | {"configs": [{"config_name": "default", "data_files": [{"split": "train", "path": "data/train-*"}]}], "dataset_info": {"features": [{"name": "image", "dtype": "image"}, {"name": "JSON_LABEL", "dtype": "string"}], "splits": [{"name": "train", "num_bytes": 161926662.0, "num_examples": 600}], "download_size": 161457126, "dataset_size": 161926662.0}} | 2023-11-30T12:28:43+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "additional_charges_roles_v1"
More Information needed | [
"# Dataset Card for \"additional_charges_roles_v1\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"additional_charges_roles_v1\"\n\nMore Information needed"
] | [
6,
22
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"additional_charges_roles_v1\"\n\nMore Information needed"
] |
a70abd99f30c7f0f0f2c0e9af3334033e43b3387 |
# Bangumi Image Base of Gosick
This is the image base of bangumi Gosick, we detected 25 characters, 2356 images in total. The full dataset is [here](all.zip).
**Please note that these image bases are not guaranteed to be 100% cleaned, they may be noisy actual.** If you intend to manually train models using this dataset, we recommend performing necessary preprocessing on the downloaded dataset to eliminate potential noisy samples (approximately 1% probability).
Here is the characters' preview:
| # | Images | Download | Preview 1 | Preview 2 | Preview 3 | Preview 4 | Preview 5 | Preview 6 | Preview 7 | Preview 8 |
|:------|---------:|:---------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|
| 0 | 98 | [Download](0/dataset.zip) |  |  |  |  |  |  |  |  |
| 1 | 36 | [Download](1/dataset.zip) |  |  |  |  |  |  |  |  |
| 2 | 167 | [Download](2/dataset.zip) |  |  |  |  |  |  |  |  |
| 3 | 92 | [Download](3/dataset.zip) |  |  |  |  |  |  |  |  |
| 4 | 29 | [Download](4/dataset.zip) |  |  |  |  |  |  |  |  |
| 5 | 24 | [Download](5/dataset.zip) |  |  |  |  |  |  |  |  |
| 6 | 24 | [Download](6/dataset.zip) |  |  |  |  |  |  |  |  |
| 7 | 100 | [Download](7/dataset.zip) |  |  |  |  |  |  |  |  |
| 8 | 20 | [Download](8/dataset.zip) |  |  |  |  |  |  |  |  |
| 9 | 16 | [Download](9/dataset.zip) |  |  |  |  |  |  |  |  |
| 10 | 16 | [Download](10/dataset.zip) |  |  |  |  |  |  |  |  |
| 11 | 10 | [Download](11/dataset.zip) |  |  |  |  |  |  |  |  |
| 12 | 10 | [Download](12/dataset.zip) |  |  |  |  |  |  |  |  |
| 13 | 28 | [Download](13/dataset.zip) |  |  |  |  |  |  |  |  |
| 14 | 762 | [Download](14/dataset.zip) |  |  |  |  |  |  |  |  |
| 15 | 13 | [Download](15/dataset.zip) |  |  |  |  |  |  |  |  |
| 16 | 12 | [Download](16/dataset.zip) |  |  |  |  |  |  |  |  |
| 17 | 18 | [Download](17/dataset.zip) |  |  |  |  |  |  |  |  |
| 18 | 10 | [Download](18/dataset.zip) |  |  |  |  |  |  |  |  |
| 19 | 45 | [Download](19/dataset.zip) |  |  |  |  |  |  |  |  |
| 20 | 535 | [Download](20/dataset.zip) |  |  |  |  |  |  |  |  |
| 21 | 11 | [Download](21/dataset.zip) |  |  |  |  |  |  |  |  |
| 22 | 27 | [Download](22/dataset.zip) |  |  |  |  |  |  |  |  |
| 23 | 32 | [Download](23/dataset.zip) |  |  |  |  |  |  |  |  |
| noise | 221 | [Download](-1/dataset.zip) |  |  |  |  |  |  |  |  |
| BangumiBase/gosick | [
"size_categories:1K<n<10K",
"license:mit",
"art",
"region:us"
] | 2023-11-30T12:50:06+00:00 | {"license": "mit", "size_categories": ["1K<n<10K"], "tags": ["art"]} | 2023-11-30T14:22:37+00:00 | [] | [] | TAGS
#size_categories-1K<n<10K #license-mit #art #region-us
| Bangumi Image Base of Gosick
============================
This is the image base of bangumi Gosick, we detected 25 characters, 2356 images in total. The full dataset is here.
Please note that these image bases are not guaranteed to be 100% cleaned, they may be noisy actual. If you intend to manually train models using this dataset, we recommend performing necessary preprocessing on the downloaded dataset to eliminate potential noisy samples (approximately 1% probability).
Here is the characters' preview:
| [] | [
"TAGS\n#size_categories-1K<n<10K #license-mit #art #region-us \n"
] | [
25
] | [
"passage: TAGS\n#size_categories-1K<n<10K #license-mit #art #region-us \n"
] |
c0625e8ee87005744a6382a46e5cd5ad9d2f2afb |
# Bangumi Image Base of Lovely Complex
This is the image base of bangumi Lovely Complex, we detected 16 characters, 1747 images in total. The full dataset is [here](all.zip).
**Please note that these image bases are not guaranteed to be 100% cleaned, they may be noisy actual.** If you intend to manually train models using this dataset, we recommend performing necessary preprocessing on the downloaded dataset to eliminate potential noisy samples (approximately 1% probability).
Here is the characters' preview:
| # | Images | Download | Preview 1 | Preview 2 | Preview 3 | Preview 4 | Preview 5 | Preview 6 | Preview 7 | Preview 8 |
|:------|---------:|:---------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|
| 0 | 49 | [Download](0/dataset.zip) |  |  |  |  |  |  |  |  |
| 1 | 663 | [Download](1/dataset.zip) |  |  |  |  |  |  |  |  |
| 2 | 29 | [Download](2/dataset.zip) |  |  |  |  |  |  |  |  |
| 3 | 458 | [Download](3/dataset.zip) |  |  |  |  |  |  |  |  |
| 4 | 46 | [Download](4/dataset.zip) |  |  |  |  |  |  |  |  |
| 5 | 23 | [Download](5/dataset.zip) |  |  |  |  |  |  |  |  |
| 6 | 25 | [Download](6/dataset.zip) |  |  |  |  |  |  |  |  |
| 7 | 62 | [Download](7/dataset.zip) |  |  |  |  |  |  |  |  |
| 8 | 17 | [Download](8/dataset.zip) |  |  |  |  |  |  |  |  |
| 9 | 110 | [Download](9/dataset.zip) |  |  |  |  |  |  |  |  |
| 10 | 39 | [Download](10/dataset.zip) |  |  |  |  |  |  |  |  |
| 11 | 40 | [Download](11/dataset.zip) |  |  |  |  |  |  |  |  |
| 12 | 64 | [Download](12/dataset.zip) |  |  |  |  |  |  |  |  |
| 13 | 20 | [Download](13/dataset.zip) |  |  |  |  |  |  |  |  |
| 14 | 43 | [Download](14/dataset.zip) |  |  |  |  |  |  |  |  |
| noise | 59 | [Download](-1/dataset.zip) |  |  |  |  |  |  |  |  |
| BangumiBase/lovelycomplex | [
"size_categories:1K<n<10K",
"license:mit",
"art",
"region:us"
] | 2023-11-30T12:50:33+00:00 | {"license": "mit", "size_categories": ["1K<n<10K"], "tags": ["art"]} | 2023-11-30T13:26:19+00:00 | [] | [] | TAGS
#size_categories-1K<n<10K #license-mit #art #region-us
| Bangumi Image Base of Lovely Complex
====================================
This is the image base of bangumi Lovely Complex, we detected 16 characters, 1747 images in total. The full dataset is here.
Please note that these image bases are not guaranteed to be 100% cleaned, they may be noisy actual. If you intend to manually train models using this dataset, we recommend performing necessary preprocessing on the downloaded dataset to eliminate potential noisy samples (approximately 1% probability).
Here is the characters' preview:
| [] | [
"TAGS\n#size_categories-1K<n<10K #license-mit #art #region-us \n"
] | [
25
] | [
"passage: TAGS\n#size_categories-1K<n<10K #license-mit #art #region-us \n"
] |
03089eee94d0ba5f5183a092e6f2ad7488f8260c | # Dataset Card for "fm-updates-llama2-chat-7b"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | coastalcph/fm-updates-llama2-chat-7b | [
"region:us"
] | 2023-11-30T12:52:57+00:00 | {"configs": [{"config_name": "default", "data_files": [{"split": "test", "path": "data/test-*"}]}], "dataset_info": {"features": [{"name": "query", "struct": [{"name": "label", "dtype": "string"}, {"name": "objects", "list": [{"name": "aliases", "sequence": "string"}, {"name": "label", "dtype": "string"}, {"name": "qid", "dtype": "string"}]}, {"name": "qid", "dtype": "string"}, {"name": "rel_id", "dtype": "string"}, {"name": "relation", "dtype": "string"}]}, {"name": "prediction", "struct": [{"name": "predictions", "list": [{"name": "answer", "dtype": "string"}, {"name": "first_token_probability", "dtype": "float64"}, {"name": "per_token_probability", "sequence": "float64"}, {"name": "perplexity", "dtype": "float64"}]}, {"name": "query", "dtype": "string"}]}, {"name": "f1", "dtype": "float64"}, {"name": "relation", "dtype": "string"}, {"name": "type", "dtype": "string"}, {"name": "original_answer", "dtype": "string"}, {"name": "updates", "sequence": "string"}], "splits": [{"name": "test", "num_bytes": 2983210.8077126252, "num_examples": 6414}], "download_size": 1236982, "dataset_size": 2983210.8077126252}} | 2023-12-06T03:31:22+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "fm-updates-llama2-chat-7b"
More Information needed | [
"# Dataset Card for \"fm-updates-llama2-chat-7b\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"fm-updates-llama2-chat-7b\"\n\nMore Information needed"
] | [
6,
22
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"fm-updates-llama2-chat-7b\"\n\nMore Information needed"
] |
70cf84239610cd4a7c0fd49656c5c498f7d0ac8d | # Dataset Card for "montresandco-dataset"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | rjaiswal/montresandco-dataset | [
"region:us"
] | 2023-11-30T13:14:29+00:00 | {"dataset_info": {"features": [{"name": "image", "dtype": "image"}, {"name": "text", "dtype": "string"}], "splits": [{"name": "train", "num_bytes": 193848798.242, "num_examples": 2033}], "download_size": 128456631, "dataset_size": 193848798.242}, "configs": [{"config_name": "default", "data_files": [{"split": "train", "path": "data/train-*"}]}]} | 2023-11-30T13:14:40+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "montresandco-dataset"
More Information needed | [
"# Dataset Card for \"montresandco-dataset\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"montresandco-dataset\"\n\nMore Information needed"
] | [
6,
17
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"montresandco-dataset\"\n\nMore Information needed"
] |
303a51b7b008d9d2cf864631fd0a2c4e51fa81aa |
# Mosaic format for filtered dedup text dataset to train Malaysian LLM
This repository is to store dataset shards using mosaic format.
1. prepared at https://github.com/malaysia-ai/dedup-text-dataset/blob/main/pretrain-llm/combine-dedup-text-dataset-filtered-4096.ipynb
2. using tokenizer https://huggingface.co/malaysia-ai/bpe-tokenizer
3. 4096 context length.
## how-to
1. git clone,
```bash
git lfs clone https://huggingface.co/datasets/malaysia-ai/mosaic-dedup-text-dataset
```
2. load it,
```python
from streaming import LocalDataset
import numpy as np
from streaming.base.format.mds.encodings import Encoding, _encodings
class UInt16(Encoding):
def encode(self, obj) -> bytes:
return obj.tobytes()
def decode(self, data: bytes):
return np.frombuffer(data, np.uint16)
_encodings['uint16'] = UInt16
dataset = LocalDataset('mosaic-dedup-text-dataset-filtered')
len(dataset)
``` | malaysia-ai/mosaic-dedup-text-dataset-filtered | [
"language:ms",
"region:us"
] | 2023-11-30T13:35:23+00:00 | {"language": ["ms"]} | 2023-12-01T07:36:30+00:00 | [] | [
"ms"
] | TAGS
#language-Malay (macrolanguage) #region-us
|
# Mosaic format for filtered dedup text dataset to train Malaysian LLM
This repository is to store dataset shards using mosaic format.
1. prepared at URL
2. using tokenizer URL
3. 4096 context length.
## how-to
1. git clone,
2. load it,
| [
"# Mosaic format for filtered dedup text dataset to train Malaysian LLM\n\nThis repository is to store dataset shards using mosaic format.\n\n1. prepared at URL\n2. using tokenizer URL\n3. 4096 context length.",
"## how-to\n\n1. git clone,\n\n\n\n2. load it,"
] | [
"TAGS\n#language-Malay (macrolanguage) #region-us \n",
"# Mosaic format for filtered dedup text dataset to train Malaysian LLM\n\nThis repository is to store dataset shards using mosaic format.\n\n1. prepared at URL\n2. using tokenizer URL\n3. 4096 context length.",
"## how-to\n\n1. git clone,\n\n\n\n2. load it,"
] | [
16,
51,
13
] | [
"passage: TAGS\n#language-Malay (macrolanguage) #region-us \n# Mosaic format for filtered dedup text dataset to train Malaysian LLM\n\nThis repository is to store dataset shards using mosaic format.\n\n1. prepared at URL\n2. using tokenizer URL\n3. 4096 context length.## how-to\n\n1. git clone,\n\n\n\n2. load it,"
] |
d029d58bbda19c5ea27ef2db6a0c4df6d509bda1 | # Dataset Card for "burger_tokens"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | erbacher/burger_tokens | [
"region:us"
] | 2023-11-30T13:51:38+00:00 | {"dataset_info": {"features": [{"name": "parameters", "dtype": "string"}, {"name": "input_ids", "sequence": "int32"}, {"name": "attention_mask", "sequence": "int8"}], "splits": [{"name": "train", "num_bytes": 1500000, "num_examples": 10000}], "download_size": 309776, "dataset_size": 1500000}, "configs": [{"config_name": "default", "data_files": [{"split": "train", "path": "data/train-*"}]}]} | 2023-11-30T13:51:39+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "burger_tokens"
More Information needed | [
"# Dataset Card for \"burger_tokens\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"burger_tokens\"\n\nMore Information needed"
] | [
6,
14
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"burger_tokens\"\n\nMore Information needed"
] |
d311eb35608c7408e601096bf96859765910fb04 | # Dataset Card for "PairDatasets_for_E5"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | ProfessorBob/PairDatasets_for_E5 | [
"region:us"
] | 2023-11-30T14:02:46+00:00 | {"dataset_info": [{"config_name": "Testset", "features": [{"name": "query", "dtype": "string"}, {"name": "passage", "dtype": "string"}], "splits": [{"name": "llm_wikitexts", "num_bytes": 355087, "num_examples": 99}, {"name": "single_document", "num_bytes": 367297, "num_examples": 148}, {"name": "philosophie", "num_bytes": 607946, "num_examples": 216}, {"name": "philosophie_small_chunk", "num_bytes": 597325, "num_examples": 323}], "download_size": 1168342, "dataset_size": 1927655}, {"config_name": "Trainset", "features": [{"name": "query", "dtype": "string"}, {"name": "passage", "dtype": "string"}], "splits": [{"name": "wikihow_summary_passage", "num_bytes": 185565003, "num_examples": 62021}, {"name": "llm_generated_question_passage", "num_bytes": 74929318, "num_examples": 20000}, {"name": "qestion_passage_fr", "num_bytes": 18560943, "num_examples": 20535}], "download_size": 160770505, "dataset_size": 279055264}], "configs": [{"config_name": "Testset", "data_files": [{"split": "llm_wikitexts", "path": "Testset/llm_wikitexts-*"}, {"split": "single_document", "path": "Testset/single_document-*"}, {"split": "philosophie", "path": "Testset/philosophie-*"}, {"split": "philosophie_small_chunk", "path": "Testset/philosophie_small_chunk-*"}]}, {"config_name": "Trainset", "data_files": [{"split": "wikihow_summary_passage", "path": "Trainset/wikihow_summary_passage-*"}, {"split": "llm_generated_question_passage", "path": "Trainset/llm_generated_question_passage-*"}, {"split": "qestion_passage_fr", "path": "Trainset/qestion_passage_fr-*"}]}]} | 2023-11-30T17:07:43+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "PairDatasets_for_E5"
More Information needed | [
"# Dataset Card for \"PairDatasets_for_E5\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"PairDatasets_for_E5\"\n\nMore Information needed"
] | [
6,
20
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"PairDatasets_for_E5\"\n\nMore Information needed"
] |
f4a6df530caf46d6bd29c05349704a47070043e3 | # Dataset Card for "mydataname"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | erbacher/mydataname | [
"region:us"
] | 2023-11-30T14:30:57+00:00 | {"dataset_info": {"features": [{"name": "parameters", "dtype": "string"}, {"name": "input_ids", "sequence": "int32"}, {"name": "attention_mask", "sequence": "int8"}], "splits": [{"name": "train", "num_bytes": 30300000, "num_examples": 10000}], "download_size": 6167011, "dataset_size": 30300000}, "configs": [{"config_name": "default", "data_files": [{"split": "train", "path": "data/train-*"}]}]} | 2023-11-30T14:30:59+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "mydataname"
More Information needed | [
"# Dataset Card for \"mydataname\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"mydataname\"\n\nMore Information needed"
] | [
6,
13
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"mydataname\"\n\nMore Information needed"
] |
1858c054667f97e9bcb6ae11aed2461414058428 | # Dataset Card for "zero-dreambooth-small"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | baptistecolle/zero-dreambooth-small | [
"region:us"
] | 2023-11-30T14:33:09+00:00 | {"configs": [{"config_name": "default", "data_files": [{"split": "train", "path": "data/train-*"}]}], "dataset_info": {"features": [{"name": "image", "dtype": "image"}, {"name": "annotation", "struct": [{"name": "description", "dtype": "string"}, {"name": "objects", "list": [{"name": "bitmap", "struct": [{"name": "data", "dtype": "string"}, {"name": "origin", "sequence": "int64"}]}, {"name": "classId", "dtype": "int64"}, {"name": "classTitle", "dtype": "string"}, {"name": "createdAt", "dtype": "string"}, {"name": "description", "dtype": "string"}, {"name": "geometryType", "dtype": "string"}, {"name": "id", "dtype": "int64"}, {"name": "labelerLogin", "dtype": "string"}, {"name": "points", "struct": [{"name": "exterior", "sequence": {"sequence": "int64"}}, {"name": "interior", "sequence": {"sequence": {"sequence": "int64"}}}]}, {"name": "tags", "sequence": "null"}, {"name": "updatedAt", "dtype": "string"}]}, {"name": "size", "struct": [{"name": "height", "dtype": "int64"}, {"name": "width", "dtype": "int64"}]}, {"name": "tags", "list": [{"name": "createdAt", "dtype": "string"}, {"name": "id", "dtype": "int64"}, {"name": "labelerLogin", "dtype": "string"}, {"name": "name", "dtype": "string"}, {"name": "tagId", "dtype": "int64"}, {"name": "updatedAt", "dtype": "string"}, {"name": "value", "dtype": "null"}]}]}, {"name": "filename", "dtype": "string"}, {"name": "embedding", "sequence": "float32"}, {"name": "cropped", "dtype": "image"}, {"name": "text", "dtype": "string"}], "splits": [{"name": "train", "num_bytes": 1083796984.0, "num_examples": 358}], "download_size": 939274079, "dataset_size": 1083796984.0}} | 2023-11-30T17:34:14+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "zero-dreambooth-small"
More Information needed | [
"# Dataset Card for \"zero-dreambooth-small\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"zero-dreambooth-small\"\n\nMore Information needed"
] | [
6,
18
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"zero-dreambooth-small\"\n\nMore Information needed"
] |
415e08dc5ca94199f049b740ddee2900717f2e8e | # Dataset Card for "tokenized_t5_small_context_len_512"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | yardeny/tokenized_t5_small_context_len_512 | [
"region:us"
] | 2023-11-30T14:34:59+00:00 | {"dataset_info": {"features": [{"name": "input_ids", "sequence": "int32"}, {"name": "attention_mask", "sequence": "int8"}], "splits": [{"name": "train", "num_bytes": 18454819544, "num_examples": 80462898}], "download_size": 6941163760, "dataset_size": 18454819544}} | 2023-11-30T14:44:48+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "tokenized_t5_small_context_len_512"
More Information needed | [
"# Dataset Card for \"tokenized_t5_small_context_len_512\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"tokenized_t5_small_context_len_512\"\n\nMore Information needed"
] | [
6,
27
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"tokenized_t5_small_context_len_512\"\n\nMore Information needed"
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.